check_missing

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

No annotations are provided, so the description carries the full behavioral burden. 'Read' weakly implies a non-mutating operation and the listed finding categories hint at the report contents, but there is no statement about scope, permissions, cost, or whether it is read-only in practice.

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?

A single efficient sentence with no filler, and the enumerated finding types are front-loaded. The phrasing 'duplicate/unmatched warnings' is slightly compressed but not wasteful.

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 must convey what comes back, and it only partly does by naming finding categories. It omits the scope of the scan and the shape of the result, leaving an agent unable to predict the response for a zero-argument call.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. No parameter-related omissions exist.

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 enumerates the categories of findings (missing/orphan files, amount mismatches, duplicate/unmatched warnings), which conveys it is an anomaly-reporting tool, but the verb 'Read' is odd for a check/validation operation and the scope (which records or claims are checked) is never stated. Nothing in the text ties it to the travel/expense/claims domain implied by its siblings.

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?

There is no statement of when to run this check, what preconditions exist, or how it relates to siblings like list_pending_claims or build_claim. The agent must infer usage entirely from the name and the enumerated finding types.

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