Loading ToolBench
Two tools with well-structured schemas and detailed descriptions. Both tools have clear, action-oriented names (gsc_*) and comprehensive parameter documentation. Descriptions are 150-200 chars, within the 10-1024 baseline. Input schemas include type definitions and descriptions for all parameters. However, output schemas are not documented in the provided code, and error handling guidance is minimal. Tool annotations (readOnlyHint) are present, which is a positive signal for protocol alignment.
Ask Google what it has actually indexed among the site's busiest pages, and why anything is not: blocked by robots, excluded by a directive, crawled and not indexed, or indexed under a different canonical. Inspects a sample, because Google rations inspections. Needs the Google login; without it this Tool says so.
How the site's results look in Google — plain blue links, rich results, FAQs, videos, and the rest — with the clicks and CTR each appearance earns. This is the only report that says whether structured data is doing anything. Needs the Google login; without it this Tool says so.
Output schemas not documented. LLMs cannot plan downstream tool calls or extract structured data without knowing what fields to expect.
Error handling lacks recovery guidance. Tools mention 'Needs the Google login; without it this Tool says so' but do not specify what error message is returned or how the agent should respond.
Parameter 'siteUrl' accepts multiple formats ('example.com', 'sc-domain:example.com', 'https://example.com/') but description does not enumerate valid formats or provide a regex pattern. LLMs may pass invalid formats.
Date parameters (startDate, endDate) use YYYY-MM-DD format but lack explicit validation constraints or examples. Description mentions 'Defaults to 3 days ago' but does not clarify timezone or whether dates are inclusive/exclusive.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | B | 79 | 2026-07-28+ | v2 |
Tool descriptions reference Google Search Console but do not explain when to use gsc_index_coverage_analysis vs gsc_search_appearance. LLMs may select the wrong tool for a given query.