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

Annotations already declare readOnly, idempotent, non-destructive, closed-world reads, so the safety bar is low. The description still earns credit by disclosing that results are illustrative examples rather than a complete inventory — a caveat an agent would not otherwise know and which affects how it should phrase answers. It stops short of describing matching/ranking behavior or result sizing.

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?

Three short sentences, front-loaded with the returned fields and followed by filters and the caveat — no filler. The opening is a verbless fragment, which reads slightly clipped but costs nothing in interpretability.

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?

A read-only, three-optional-parameter lookup with no output schema; the description covers what is returned, how to filter, and the key limitation of the dataset. Nothing an agent needs in order to call it correctly is missing.

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 67%, so the baseline is 3. The description does add real value for the weakly documented fields, clarifying that the query matches against name, controls, and evidence rather than just a title. It adds nothing for the four enum values under status, which neither the schema nor the description explains.

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?

Names the resource (use cases) and lists what each record carries — status, customers, claims — plus the three available filters, so an agent knows precisely what it gets back. The verb is implicit rather than stated ('Use cases with status...'), and it does not explicitly contrast with the similarly named sibling find_processes, so it stops short of a 5.

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?

Usage is implied through the filter list rather than stated: the description tells you the tool can be narrowed by vertical, status, or query, but never says when to choose it over alternatives such as find_processes or list_claims. No prerequisites or exclusions are given.

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