Add Labels to a Niche

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

Goes well beyond the annotations: discloses return keys (`added`, `alreadyPresent`), all-or-nothing atomicity with the specific failure triggers (unknown id, view-only Space) and that the error enumerates offending ids, idempotency ('a repeat is safe'), zero cost, and a per-niche rate limit. Annotations only say readOnly=false, destructive=true, openWorld=false; the description supplies the operational reality.

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-loaded with the action, then constraints; nearly every sentence carries distinct information (undo path, auth, atomicity, idempotency, cost, rate limit). The dense run-on sentence about atomicity and the parenthetical error detail slightly hurt scannability.

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 2-param mutation with no output schema, the description covers everything an agent needs: permission requirements, failure modes, idempotency, rate limits, and the shape of the response. Nothing material is left to inference.

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 params are already documented, so the baseline is 3; the description adds value by framing `labelIds` as a batch that should be sent in a single call and by stating the per-id failure/counting semantics. It does not restate the 1-100 bound or integer type, which the schema already covers.

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 ('put a niche in one or more labels') and immediately differentiates itself from the inverse sibling by naming `remove_niche_labels` as the undo path. An agent can distinguish this from `add_niche_spaces` or `remove_niche_labels` without opening any schema.

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 when-to-use (adding label membership), the inverse operation for undo, and a concrete batching instruction ('put every id in one call') tied to the 2-calls-per-minute limit. It also names the prerequisite role and tells the agent what to do instead of retrying on a 403.

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