recall

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

No annotations are present, so the description fully bears the responsibility of disclosing behavior. It details the ranking method (cosine similarity over embed-text composition) and mentions the output includes scores. However, it does not explicitly state that the operation is read-only or has no side effects, which would be helpful for a query tool.

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 concise and well-structured: a brief purpose paragraph followed by structured Args and Returns sections. Every sentence adds value without redundancy.

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?

The tool has two parameters, no nested objects, and an output schema exists. The description adequately explains the tool's function and return structure. It references an internal ADR, which may not be meaningful to all agents, but overall the description is sufficiently 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 input schema has 0% description coverage, so the description must add meaning. It clearly defines 'query' as a natural-language query and 'limit' with range (1-100) and default 10, providing crucial context not present in the schema (which only shows default).

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 explicitly states the tool performs 'semantic recall over captured payloads by natural-language query', clearly indicating the verb (recall), resource (captured payloads), and method (natural-language query). It distinguishes from siblings like 'capture_url' and 'list_captures', which focus on different operations.

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 explains the tool ranks captures by cosine similarity and returns top-k results, but it does not explicitly specify when to use this tool versus alternatives (e.g., 'list_captures' for exact listing, 'get_capture' for a single capture). No exclusion or prerequisite guidance is provided.

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