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

Annotations only cover the safety profile (readOnlyHint, openWorldHint), and the description adds substantial context beyond them: the visits permission requirement, the shared 60-per-hour rate budget with cromanion_visits, and semantic notes on output fields (`observed` supersedes `reading` post-conversion, `shown.seen` is browser-confirmed rather than sent).

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?

Front-loaded with the role of the tool, then identifiers, permission, and field semantics. Information-dense with little waste, though the output-field explanations run a bit long for a tool that also ships an output schema.

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 a read-only tool with three optional parameters, an output schema, and 100% schema coverage, the description supplies everything an agent needs: what it returns conceptually, which IDs to pass, permission requirements, and rate limits.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning: it frames visitId/sessionId as mutually alternative entry points and notes the timing constraint on sessionId. It adds incremental value over the schema rather than merely restating it.

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?

Names a specific resource and scope: 'One visit in full' with the story of each page load, agent decisions, visitor-visible outcome, and doubts. It clearly distinguishes itself from cromanion_visits (the list) and cromanion_live (in-flight sessions) without the agent needing to open either schema.

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?

Explicitly states which identifiers to supply and where they come from — `visitId` from cromanion_visits, or `sessionId` from cromanion_live 'once that visitor has left' — plus the required visits permission. The alternative-selection condition is spelled out rather than implied.

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