verification_state

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

Annotations already indicate readOnly and idempotent, so the description adds value by explaining the behavioral nuance: 'With files, runs only count when project-wide or scoped to those files.' This clarifies how file filtering affects the result, going beyond the 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?

Two well-structured sentences, front-loaded with purpose, no redundant or extraneous information. Every sentence contributes to understanding.

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?

For a read-only state-view tool with an output schema, the description is fairly complete. It explains the core summary and the file-scoping behavior. However, it lacks guidance on when to use this tool vs siblings like diagnostic_refresh, and does not mention any prerequisites or limitations.

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%, and the description only minimally addresses one parameter ('files') by describing its effect. The other five parameters (projectId, projectRef, sources, limit, cacheStalenessMs) receive no explanation, leaving the agent to infer their semantics from names alone.

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 states it is a 'verification state view' that summarizes coverage of cached diagnostic runs over the working-tree overlay. It lists specific aspects like file-scoped recent runs, watcher diagnostic state, and suggested actions, which distinguishes it from sibling tools that produce artifacts or perform updates.

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 does not explicitly state when to use this tool versus alternatives like diagnostic_refresh or verification_bundle_artifact. It implies usage for checking coverage but provides no exclusions or comparative guidance, which is a gap given the many siblings.

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