MCP Server for hierarchical recursive summary tree construction from lengthy text, condensing conversational or execution traces via recursive clustering.
Single tool with minimal definition quality. Tool name 'condense_context_tree' lacks action verb prefix (should be 'summarize_' or 'condense_'). Description is 73 chars but lacks WHEN to use, prerequisites, or output structure guidance. Input schema present but parameter 'text' has NO description, violates critical rule that every parameter needs a description. No output schema documented, LLMs cannot plan downstream calls. No error handling guidance. Tool does one thing but definition is severely underdocumented.
Construct hierarchical recursive summary tree from lengthy text.
Parameter 'text' has no description. Critical rule violation: every parameter must explain what it controls. LLMs cannot infer that this accepts arbitrary-length text vs. structured JSON vs. file paths.
No output schema documented. LLMs need to know what fields to expect (tree_depth, leaf_count, compression_ratio, root_summary, leaf_summaries). Without this, agents cannot plan downstream calls or extract the right data.
Tool name 'condense_context_tree' does not start with a clear action verb. Baseline: 90% of A+ tools start with get, list, create, search, update, send, delete. Consider 'summarize_text_hierarchically' or 'build_context_summary'.
Tool description (73 chars) lacks WHEN to use it and prerequisites. Should answer: What does it do? When should the LLM call it instead of a similar tool? What does it return? Current description is incomplete.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 36 | 2026-07-28+ | v2 |
No error handling guidance. If text is empty, malformed, or exceeds limits, the tool returns no recovery hints. Error responses must tell the LLM what to do next.