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

Goes well beyond the annotations: it discloses partial-update semantics ('Only the dimensions you send change; an empty list clears one'), which explains why destructiveHint=true matters, plus authorization requirements, a per-workspace rate cap, and a state-based lock. This is the kind of context an agent cannot infer from readOnlyHint/destructiveHint alone.

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?

Five tight clauses, front-loaded with the action and side effect, then constraints in descending importance. Every sentence carries information; nothing is filler.

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 an output schema present, return values need not be explained, and the description covers the mutation, auth, rate cap, and lock. The only soft spot is 'Locked while the first brief runs', which is slightly cryptic about when the lock releases.

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 each dimension has a label, so the schema does the naming. The description adds the critical merge semantics ('empty list clears one') not present in the schema, but it does not clarify the format of the list values (e.g. free strings vs controlled vocabulary) for the eight dimension arrays.

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 ('Sets the ideal customer profile') and adds the downstream side effect ('re-reads how much each tracked competitor overlaps it'), which no sibling does. An agent can distinguish this from update_company_profile or add_competitor from the text alone.

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 real preconditions: 'Admin only', 'Counts toward a daily cap per workspace', and 'Locked while the first brief runs'. These tell the agent when the call will be rejected, though no alternative sibling (e.g. update_company_profile) is named for the non-admin or locked case.

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