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

Annotations already declare it as a safe, read-only, idempotent operation, but the description adds valuable behavioral context beyond them: it is 'Free', it returns 'an address for each hit that you pass straight to `fetch`', and an empty query lists the most recent work. These details help the agent understand cost, output shape, and a non-obvious default behavior.

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 front-loaded with the key information ('Free. Finds anything...') and progresses logically through what it matches, what it returns, when to use it, and the empty-query behavior. The example phrases are illustrative without being wasteful.

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?

Given the tool's complexity, the full schema description, and the absence of an output schema, the description is complete enough: it explains the search mechanism, the return format, the empty-query fallback, and the kind parameter's narrowing role. No critical information is missing for correct invocation.

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 four parameters thoroughly. The description adds only minor color (e.g., 'page URL' as a query example) and largely repeats the schema's semantics, so the baseline of 3 is appropriate.

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 a specific verb ('Finds') and resource ('anything in this workspace by words'), and enumerates the types of things it matches (domain, page URL, client name, caption, project). It distinguishes itself from siblings by explaining that each hit returns an address to pass to `fetch`, which separates it from content-fetching tools.

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?

It provides explicit when-to-use guidance with a concrete trigger ('Use this the moment somebody refers to work they have already done') and several realistic examples. It also gives an alternative path for a specific case ('Use kind=audit to find audits directly') and defines the empty-query behavior, leaving little ambiguity about when to invoke it.

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