find_similar_sections

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses the algorithmic steps, signals fused, clustering method, ranking criteria, and verdict tiers. This goes well beyond the input schema, but could be more explicit about rate limits or side effects (though declared read-only).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with two sentences, front-loading the purpose. The technical details are dense but efficient. A slight improvement would be to break the long sentence for readability, but it remains clear and without fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description explains the algorithm and verdicts but omits the output format (e.g., structure of returned clusters). Given the tool's complexity and the lack of an output schema, this gap reduces completeness. Sibling context is not addressed, but the description is otherwise thorough for a moderately complex tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 67%, and the description does not directly elaborate on individual parameters. However, it provides algorithmic context that helps interpret parameters like min_score and near_duplicate_threshold. It adds some value but does not fully compensate for the partly undocumented parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it performs multi-signal section dedup detection using specific algorithms (embedding cosine, lexical Jaccard, union-find clustering) and outputs verdict tiers (near_duplicate, overlapping_topic, parallel_tutorial). This is a precise verb+resource combination that distinguishes it from sibling tools like 'get_related_sections' or 'section_neighbors'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not provide explicit guidance on when to use this tool versus alternatives. It only mentions 'Read-only' but lacks context such as prerequisites, ideal use cases, or when not to use it. With many section-related siblings, the absence of differentiation criteria is a significant gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.