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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds meaningful behavioral context: signals refresh nightly while strategy updates weekly, and undiagnosed workspaces will be reported as such rather than invented. It also discloses cost (free, no AI credits), which is not present in annotations. No contradictions.

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 4-sentence paragraph that front-loads the core purpose, then adds refresh cadence, non-fabrication behavior, scoping, and cost. Each sentence provides distinct, useful information with no filler or repetition. Slightly longer than minimal but every clause earns its place.

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?

Combined with the output schema and annotations, the description covers the tool's purpose, freshness, scoping, cost, and an important edge case (undiagnosed workspace). It does not detail return values, but the output schema handles that. For a 3-parameter tool with an enum, this is sufficiently complete for correct invocation.

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 100%, so the input schema already documents action, signal, and user_intent thoroughly. The description adds the meta-note that no domain/site parameter is needed, which clarifies invocation but does not add deeper semantics to the existing parameters. Baseline 3 is appropriate given full schema coverage.

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 defines the tool as 'the agent's cached diagnosis for this workspace' and enumerates four concrete components (snapshot, strategy, raw signal, content scores). It states the resource and scope, and distinguishes itself by being workspace-scoped and requiring no domain/site parameter. However, it doesn't explicitly name a verb like 'get' or 'retrieve' or compare against a specific sibling.

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?

Provides clear context that the tool is already scoped to the connected workspace and site, so agents can call it directly without domain/site parameters. This implies when to use it (for cached diagnosis of the current workspace) but does not explicitly mention alternatives or when-not conditions. The refresh cadence hints at staleness but does not guide agents to other tools for fresher data.

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