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

Beyond the readOnly/idempotent annotations, it discloses genuine behavioral caveats: no match is not proof of no activity, done is not proof of delivery, hasMore interacts with a shared read budget, and it avoids opening the app or returning draft bodies. This is exactly the kind of context annotations cannot carry.

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 purpose is front-loaded, but the text sprawls into meta-instructions ('Stop when the requested statuses and their evidence limits are clear') and a trailing 'Read-only.' that merely repeats the annotation. Several sentences could be trimmed without losing guidance.

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?

Given an output schema exists, return values need not be explained, yet the description covers the relevant semantics (compact status, openCardCount, reviewUrl, hasMore) plus search limitations. It is complete for correct invocation, with only the redundant return-value detail as a minor overreach.

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% and both parameters (queries, limit) are already documented with their bounds and the hasMore caveat in the schema itself. The description only echoes batching ('Batch names in one call'), adding little semantic detail beyond the structured fields, 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 and resource ('check whether work for named people or topics already has a review card') and immediately bounds scope to 'titles and prompts only'. It also names the sibling it is not, review_get, so an agent can distinguish the two without opening 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?

Gives explicit routing: use review_get when full draft or evidence is needed, use ask_revnu for missing account evidence, and report matching records for a named status lookup. It also states batching behavior ('Batch names in one call') and the stop condition, leaving little to inference.

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