memo_ask

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

Annotations declare readOnlyHint=true and idempotentHint=true; the description adds crucial 'best-effort auto-capture side effects', which is a behavioral trait not captured by annotations. No contradiction.

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?

Two sentences with no fluff, front-loaded purpose. The second sentence combines usage and parameter hints efficiently. Could benefit from bullet points but remains clear and concise.

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?

Covers primary purpose and usage but does not address session_id or include_repos. Output schema exists but description does not mention return format. Adequate for a read-only tool with annotations, but incomplete for the parameter count.

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?

With 0% schema description coverage, the description partially compensates by explaining that k, type, and snippet_chars tune retrieval and source consults logging. However, it omits question, session_id, and include_repos, leaving significant gaps for a 7-parameter tool.

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?

Clearly states the tool answers a question using memo retrieval and citations, distinguishing it from raw hit lists (sibling memo_search). The verb 'answer' and resource 'question' are specific and actionable.

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?

Explicitly instructs 'Use when you want a synthesized answer grounded in durable memories instead of raw hit lists', which directly contrasts with memo_search. Also notes best-effort auto-capture side effects, providing clear context.

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