Search claims

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds valuable behavioral context beyond that: it is budgeted and may drop bodies at tighter budgets, it never shows superseded/rejected/resolved claims, it returns compact lines without bodies, and it lists newest ids last. The only minor gap is that it doesn't explicitly state whether the result is paginated or how the budget mechanism behaves in detail, but the description carries substantial weight beyond the annotations.

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 dense but every sentence earns its place: it states the core function, the output format, the cost/behavior tradeoffs, the when-to-use guidance, the alternative tool, and the no-arguments behavior. It is front-loaded with the most important facts (read-only, compact output) and uses the back half for edge-case behavior. No filler or repetition of schema details.

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 read-only list/search tool with no output schema, the description covers everything an agent needs: what it returns, what it omits, when to use it, how filtering works, and how it differs from the projection and from 'why'. The parameter descriptions in the schema fill in the remaining details (enums, defaults). The only thing not explicitly stated is the exact default limit (50), but that is in the schema, so the description need not repeat it.

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 100%, so the schema already documents all five parameters well. The description adds meaningful extra semantics: it explains that 'query' matches against id, title AND body (a detail the schema also mentions but the description reinforces with the rationale about remembering claims by reasoning details), and it warns that substring matching is not semantic search. It also explains the 'project' parameter's behavior inside a repo with .continuity/. This goes beyond the baseline 3 for full coverage.

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 states a specific verb ('List or search'), a precise resource ('the claim set directly, bypassing the resume projection'), and immediately distinguishes itself from the projection and from the sibling 'why' tool. It also enumerates the output shape (one compact line per claim with status, type, id, title), so an agent knows exactly what this tool returns and how it differs from alternatives.

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 gives explicit when-to-use guidance: 'Reach for this when the projection is not enough' and explains the exact conditions (budgeted, bodies dropped, open questions omitted, superseded/rejected/resolved never shown). It also names the alternative for one claim's detail ('use `why`'), and the schema's parameter descriptions reinforce when to use filters like status='superseded' or 'rejected'. This is exemplary routing guidance.

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