tk_coverage

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: every gap carries a fallback saying where to look instead, and the result always includes a non-empty list of known gaps — semantics an agent cannot infer from the annotations alone.

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?

Structure is front-loaded: the imperative purpose first, then the usage condition, then the return summary. It is slightly longer than strictly necessary because the gap rationale is stated twice in adjacent sentences, but every element is relevant and there is 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?

With an output schema present, the description is not obligated to explain return values, yet it still names the Coverage payload, its families, as-of note, and non-empty gap list. Combined with the rich annotations and explicit call conditions, an agent has everything needed to invoke this correctly.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly implies a parameterless invocation and spends no space on non-existent inputs.

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 a specific verb and resource: 'Declare what this connector covers, how it is sourced, and what it does NOT cover.' That is unmistakably distinct from the sibling read tools (search_judgments, get_judgment_text), which fetch records rather than declare coverage metadata.

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 explicit trigger conditions: call before asserting the TK record 'does not contain' something, and whenever a search returns empty. It also explains why — an empty result may be a connector gap rather than a record gap — which directly routes the agent away from over-claiming based on sibling search results.

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