extract_recent

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

Annotations (readOnlyHint:false, destructiveHint:false) are neutral, and the description adds behavioral details by explaining the scanning and enqueuing process with specific heuristic conditions. It clarifies the tool's role without contradiction.

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 relatively concise with a clear summary and a bulleted list of heuristics. However, it lacks structure for parameter explanations and could be more organized (e.g., separating summary from details).

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 description explains the heuristics in detail but omits parameter semantics and the exact output format (though output schema exists). It is partially complete for a moderately complex tool but has gaps.

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 two parameters (window_min, max_messages) with 0% description coverage. The tool description does not explain what these parameters mean or how they affect behavior, leaving the agent without enough context to set them correctly.

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 'Scan recent dialog_messages and enqueue heuristic candidates' with specific verb and resource. It lists four distinct heuristics (H1-H4) with conditions, distinguishing it from sibling tools like 'review_candidates' or 'pickup_candidates'.

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 provides no explicit guidance on when to use this tool versus alternatives like 'review_candidates' or 'pickup_candidates'. It implies a preprocessing step but lacks usage context or exclusion criteria.

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