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

Annotations already establish read-only/idempotent, but the description goes further: it names the required credential, the claimed-workspace requirement, and the concrete failure mode (sandbox key from self-registration is refused with 403 until a person claims the workspace). That 403 detail is exactly the kind of auth/error context annotations cannot express.

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 tight sentences, front-loaded with what is listed, then how to filter, then the two gating conditions. The only slack is 'Read-only,' which restates readOnlyHint=true, though placing it with the auth constraints reads naturally.

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?

For a single optional-enum parameter with no output schema, the description supplies the return shape, the filter default, and both access prerequisites including a specific error code. Nothing an agent needs in order to call this correctly and interpret a 403 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 100%, so the enum values are already documented; the description adds the non-obvious default semantics — that omitting status returns all statuses rather than none. That is genuine meaning beyond the schema's 'Only mappings with this status.'

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 ('List the mappings Rosetta held back'), plus scope ('for a person or agent to approve') and the exact fields returned (source, proposed canonical field, confidence, status). This clearly separates it from the decision sibling decide_rosetta_review, which acts on a single mapping rather than enumerating them.

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 filter behavior — pass pending/approved/rejected to narrow, omit to get everything — and states two hard prerequisites (Last Price credential, claimed workspace). It doesn't explicitly say 'to approve a mapping, use decide_rosetta_review,' so the sibling routing is only implied by the word 'approve'.

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