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

Annotations only supply the safety profile (readOnly=false, destructive=false, openWorld=true); the description adds substantive behavior: recent engines are served from cache at no cost, the call consumes a monthly allowance, and retries must reuse the same idempotency_key. These cost and caching semantics are exactly the context an agent needs before invoking.

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?

Four tightly packed sentences, purpose front-loaded, then caching, cost, and idempotency guidance in descending order of importance. No filler or repetition of the title.

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?

An output schema exists so return values need not be described, and annotations cover the safety profile. The description covers caching, allowance, and retry handling, but omits edge behavior such as what happens when the monthly allowance is exhausted, which is relevant for an open-world, quota-consuming call.

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 description coverage is 0%, so the description must carry the load. It explains idempotency_key usage well (unique value, same value on retry) but says nothing about question_id beyond the implicit 'one tracked question', leaving the UUID requirement undocumented in both places.

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 ('Ask the plan's AI engines one tracked question now and record whether each cites the brand'). The 'now' / on-demand framing cleanly separates it from passive sibling reads like list_citations or list_visibility_events.

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?

Conveys the operating context (on-demand check for a tracked question, cached results reused, allowance consumed), which implies when it is appropriate. However it never names an alternative (e.g. list_citations for existing results) or states when not to use it, so routing is left to inference.

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