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

Annotations already declare readOnlyHint and non-destructive, so the description correctly adds extra context: the required sources API scope, the successRate definition (finished runs only, so in-flight crawls aren't failures), and English as fallback for untranslated fields. These enrich the behavioural model beyond the annotations without contradiction.

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 a single, dense paragraph that front-loads the core purpose and then lists specific metrics and caveats. It is efficient, though slightly packed; each sentence adds value, but it could be trimmed for readability without losing content.

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 output schema exists, the description does not need to explain return values. It covers the key behavioural nuance (successRate), auth scope, language fallback, and the distinction from profile data. Missing details like pagination or additional filtering are minor and likely covered by schema or context. Overall, it is sufficiently complete for a read-only metrics tool.

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 50% (only 'days' has a description; 'key' has none). The tool description does not discuss parameters at all, so it fails to compensate for the missing 'key' semantics. The agent gets no added meaning beyond the schema for either parameter.

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 opens with 'Measured newsroom behaviour' and immediately clarifies it is about what the newsroom did rather than its profile, explicitly listing the metrics (crawl outcomes, byline, originality, opinion, press-release, filing-lag rates). This clearly distinguishes it from profile-focused siblings like sources_get and sources_list, making the tool's purpose unambiguous.

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 contrasts actual behaviour with profile claims, implying use for behavioural data vs. static profile data, which is helpful for selection among siblings. It also gives a critical caveat about successRate being over finished runs only. However, it does not explicitly name alternative tools or state when not to use it, leaving some inference to the agent.

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