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

Annotations declare readOnlyHint=true and openWorldHint=false, so the safe read behavior is already captured. The description adds the notion of 'deep search' and that results are 'relevant API endpoints,' but doesn't disclose specifics like whether it searches full content or just metadata, pagination, or result limits. It also doesn't state that it's case-insensitive (that's in the schema), but that's fine. Overall, some added context but not rich behavioral detail beyond 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 two sentences with no filler. It states what the tool does, when to use it, and how to use the results—all in a front-loaded manner. Every sentence earns its place and it is appropriately sized for a single-parameter search tool.

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 only one parameter and no output schema, the description covers the purpose, usage, and output chaining. It lacks some behavioral details like whether results are paginated or how many results are returned, but given the simplicity, these seems minor. The tool appears complete enough for an agent to invoke correctly.

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% because the only parameter 'pattern' is described in the schema as 'Search pattern (case-insensitive)'. The description doesn't add additional meaning about the parameter format beyond implying it's a keyword search. Since coverage is high and the description reinforces the purpose, a score above baseline is justified, but not the maximum because there's no extra detail about how patterns are matched (e.g., regex, wildcards).

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 it 'Performs a deep search through paths, operations, and parameters to discover relevant API endpoints.' It identifies the specific verb (search) and resource (API endpoints) and differentiates itself from siblings like 'get-endpoint' and 'list-endpoints' by focusing on discovery via search rather than retrieval or listing. However, it doesn't mention the 'pattern' parameter by name, though the purpose is understandable.

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 tells when to use it: 'Use this tool to find specific API capabilities, required parameters, or data models based on search keywords.' It also indicates how to chain the results: 'Results can be passed directly into 'get-endpoint'.' This gives clear context for when to invoke this tool versus alternatives, though it doesn't explicitly state when NOT to use it (e.g., when you already have an endpoint ID).

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