Ask Documentation Agent

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower, but the description still adds substantial context: the default response is a synthesized answer plus citations, and include_chunks increases token usage ~3x. That cost/behavior disclosure is genuinely useful and goes beyond what the annotations provide.

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?

Well-structured and front-loaded, with the purpose stated first and clear bolded sections for workflow, required/optional params, and query examples. It is somewhat long, and the Required/Optional bullet list partially duplicates the schema, costing it a point on strict conciseness.

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?

For a 6-parameter tool with no output schema, the description compensates by describing the return shape (synthesized answer + citations, or structured JSON) and the token tradeoffs of retrieval options. An agent has everything needed to call it correctly and anticipate the response.

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 coverage is 100%, so the baseline is 3 and the schema already documents all six parameters, including the top_k/include_chunks dependency. The description adds some value by giving concrete store examples and framing query as natural language, but much of the Required/Optional section restates what the schema already says.

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?

States a specific verb+resource ("AI-powered semantic search for complex documentation questions") and scopes it precisely to "conceptual queries, multi-part research, and understanding how systems work." There are no siblings to differentiate from, but the description also distinguishes itself from naive keyword search by explicitly rejecting single-keyword queries.

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?

Provides explicit when-to-use guidance (conceptual, multi-part research), when-not-to-use (❌ "authentication" too vague, single keywords), a step-by-step workflow, and a concrete method for discovering valid store values via the MCP Resources list. Nothing about selection or prerequisites is left to inference.

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