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

Annotations only declare readOnlyHint=true, and the description materially extends that: it resolves the POST/read-only tension ("Read-only despite being a POST — the query goes in the body") and discloses the return scope ("Returns metadata only") as well as the underlying endpoint. These are behavioral facts beyond the annotation.

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, no waste, all front-loaded: purpose, return scope, and the behavioral caveat appear before the endpoint reference. Every clause earns its place.

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 search tool with readOnlyHint and no output schema, the description covers purpose, query syntax, return scope, and the POST caveat. Pagination is only handled in the schema (start/size), so the description is slightly light on how to page, but otherwise complete.

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 query, size, and start parameters are already documented. The inline example query (metadata.customer_id:"cus_1") largely mirrors the schema's own example, adding only marginal meaning beyond what the schema provides; baseline 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?

States a specific verb (search) and resource (tokens) and clarifies the scope: query syntax over metadata with metadata-only returns. This naturally separates it from list_tokens and get_token, but no sibling is named explicitly, so it stops short of a 5.

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 implies when the tool applies (query-based filtered search) but gives no explicit when-to-use/when-not guidance, nor does it route the agent away from list_tokens or get_token for related needs. Usage is inferable rather than stated.

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