list_rejections

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

Annotations already declare readOnly/idempotent/non-destructive, so the description's added value is defining the near_duplicate semantics (stored anyway but logged) and the returned fields (reason codes, detail, similarity). This is meaningful context beyond the safety profile, though it doesn't discuss volume/pagination limits of the list.

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?

Front-loads what is listed, then the near_duplicate clarification, then usage. Dense but each clause carries information; slightly long but no filler.

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?

With no output schema, the description correctly summarizes return contents (reason codes, detail, similarity). It omits behavior of unlimited queries (default/clamp) but that is covered in the schema, leaving the definition complete for an agent to call it.

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 both limit and reason are fully documented there (default 50, clamp 1..=500, example reason codes). The description only restates that optional limit and reason filters narrow the audit, adding no syntax or behavior beyond the schema, so the baseline 3 applies.

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+resource ('List quality-gate flags and rejections') and then defines the two distinct categories it covers: discarded memories and stored-but-logged near duplicates. An agent can distinguish this audit tool from the retrieval siblings without reading schemas.

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?

Explicitly scopes usage with 'Use only to diagnose a missing capture, a flagged near duplicate, or when the user asks what Wenlan rejected,' which tells the agent when-not to reach for it. It stops short of naming a specific alternative sibling (e.g. recall) for normal lookups, so not a full 5.

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