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

With annotations declaring readOnly=false, destructive=true, openWorld=true and idempotent=false, the description still adds meaningful context: result caching within a few hours, consumption of a monthly quota, and retry semantics via a stable idempotency_key. The destructiveHint is only partially explained through quota consumption, but the caching and retry details are genuinely beyond what the annotations expose.

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 short sentences in a sensible order: what it does, cost/caching behavior, quota impact, retry instruction. Front-loaded and no filler, though the cost and caching points could be merged without losing meaning.

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-value explanation is unnecessary, and the description covers the awkward parts (caching, quota, idempotency). It leaves open what happens if question_id does not reference a tracked question and why a 'check' carries destructiveHint=true.

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 0%, so the description must carry both parameters. It handles idempotency_key well (unique value, reused on retry), but question_id is only obliquely covered by 'one tracked question' and never states that it must be a UUID referencing an existing question in the plan.

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?

The description states a specific verb+resource+outcome: ask the plan's AI engines a tracked question 'now' and record whether each cites the brand. That is far more specific than the title alone, though it never names the natural alternatives (list_citations for historical results, check_citation_readiness for static readiness) so an agent must infer the split from wording 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?

It gives real operational context for choosing to call it: recent engine results are served at no cost, and calls draw on the workspace's monthly on-demand allowance. It lacks an explicit 'use X instead when...' routing statement and does not say when a fresh check is genuinely warranted, so the guidance is strong but not complete.

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