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

While annotations already declare readOnlyHint=true and openWorldHint=true, the description adds useful context: it returns a 'structured, audited deliverable' and mentions server-side validation. It does not disclose rate limits, error behavior, or implications of the 'agent-payable' label, but the core safety profile is clear and consistent with annotations.

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?

The description is verbose and mixes purpose, multiple example questions, a reference case in French, and an ambiguous instruction. While it front-loads the main function, the structure is disjointed and would benefit from clearer separation of use cases, parameter guidance, and examples. It is not overly long, but it could be more concise and organized.

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?

Given the tool's complexity (7 parameters, no output schema, low schema coverage), the description provides a rich set of use cases and a general sense of the deliverable, but it omits critical parameter semantics and potential edge cases. An agent would still need to infer/guess parameter meanings from partial examples. It is not complete enough for confident invocation without additional schema exploration.

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?

With only 14% schema description coverage (only 'async' is described), the description had a responsibility to explain parameters like entity_type, sentiment_lens, date_range_days, and language_filter. It only hints at them through example questions (e.g., 'last 7 days' for date_range, 'competitors' for include_competitors) but does not clarify allowed values or semantics. The phrase 'send the documented case fields' is cryptic and unhelpful.

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 clearly identifies a media/sentiment analysis tool with distinct capabilities: tracking 7-day PR/brand sentiment, detecting emerging crises, monitoring launch coverage, comparing competitors, and recommending executive actions. It uses active verbs ('returns', 'detects', 'tracks', 'compares') and concrete outputs, distinguishing it from generic media tools among siblings.

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?

The description offers multiple concrete example questions that map to specific use cases (crisis detection, launch tracking, competitor comparison, comms prioritization), making it clear when to invoke the tool. However, it does not explicitly state when not to use it or compare it to alternatives like 'trend_watcher' or 'reputation_engine', stopping short of full usage guidance.

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