search_evidence

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description still adds real value beyond that: it discloses the result cap ('at most `limit` notes') and explains what the returned records actually contain (paraphrased statements with source and locator).

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?

Three short sentences, front-loaded with what is being searched, then filters, then intended use, then return behavior. No filler or restated boilerplate.

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?

With no output schema, the description should sketch the return shape, and it does note that hits are notes with source and locator and that results are capped. Missing only minor details like default limit, ordering, or whether an empty query returns everything.

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 0% and the schema has no enums, so the description must carry the burden – and it does: free-text `query`, example domains ('launch', 'brand', 'collaboration'), and the era vocabulary (E0–E8 or 'cross'). Only `limit`'s default of 10 is left to the schema.

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 and resource ('search the evidence notes') and even characterizes the resource as 'paraphrased statements with source and locator,' which an agent can't get from the schema. It doesn't explicitly distinguish itself from the sibling `search` tool, but the corpus is named precisely enough to be 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?

Gives an explicit intended use ('Use to answer "what is the evidence for…"') and enumerates the filtering dimensions, which is clear context for when to reach for it. It stops short of stating when not to use it or when to prefer the generic `search` sibling.

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