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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses useful behavior: case-insensitive substring matching, exclusion of file contents, a 20-result cap, the exact id format ('site:<site_id>' or 'file:<site_id>:<path>'), and the fact that url is the live address. This gives an agent a clear model of what the call will do.

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 four tightly written sentences with no filler. The most important constraints are front-loaded, and every sentence contributes either scope, result format, or a follow-up instruction.

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 single-parameter read-only search tool, the description covers everything needed to call it correctly: searched fields, exclusions, result limits, id semantics, empty-query behavior, and the recommended next action. The output schema exists for detailed return fields, so the description is appropriately 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?

The schema already documents the query parameter with 100% coverage, establishing the baseline at 3. The description adds meaningful semantic detail beyond the schema: matching is case-insensitive, operates on substrings, excludes file contents, and an empty string lists the user's sites.

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 action and resource: searching the authenticated user's own sites. It enumerates the exact searchable fields (subdomain, custom domain, title, description, file path) and explicitly excludes file contents, making it clearly distinct from siblings like list_sites and fetch.

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 clear context for when to use the tool: searching a user's own sites by metadata or file path, with an explicit empty-query mode for listing sites. It also directs the agent to use fetch with a returned id to read the result. It does not cross-reference list_sites as an alternative, but the core usage guidance is actionable.

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