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

The quota disclosure — 'Uses one monthly library lookup' — is exactly the kind of context annotations can't convey, and it explains why readOnlyHint is false despite the read-flavored verb. Space scoping behavior is also clarified. Missing: what happens if the lookup fails or the allowance is spent.

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, each carrying distinct information, with the primary action and the cost implication up front. No 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?

For a small two-parameter tool with no output schema, the description covers purpose, cost, and scoping well. It doesn't say what comes back after the refresh (refreshed ad payload, a trigger acknowledgment, or a job) or how failures surface, which matters for an agent deciding whether to read results immediately afterward.

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 the space_id description in the schema is already thorough; the description essentially restates it rather than adding new meaning. competitor_id gets no added semantics beyond the schema's bare 'The competitor id.'

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 — pulling a competitor's ad libraries on demand rather than waiting for the daily refresh. This is clearly distinguishable from the read-only siblings like list_competitor_ads or get_competitor, since the point is triggering a fetch now.

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?

Explains exactly when to use it: when you need the data before the next scheduled refresh. Also gives the scoping alternative via set_active_space or a per-call space_id override. It doesn't mention what to do when the monthly allowance is exhausted (get_competitor_allowance), which would complete the guidance.

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