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

With no annotations, the description carries the full burden and does so: it discloses the implicit state change (starting an unstarted visit), the exact refusal condition and error code, the permission model, the override mechanism and its audit trail ('recorded and audited'), and a hard restriction on agents. That is far more than a restatement of the schema.

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?

Three dense sentences, front-loaded with the action and side effect, then permissions, then the refusal/override rules. Every clause carries operational information an agent needs; nothing is padding.

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 mutation tool with an output schema already covering return values, the description supplies everything else an agent needs: eligibility, side effects, failure mode, and the one sanctioned override path. No material gap remains.

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 only 33%, so the description must compensate, and it does for the two undocumented fields: note is framed as optional context on completion, and override_reason is thoroughly explained (owner in person, hosted override page, audit consequence). visit_id is only implied as the target visit, leaving its semantics to the uuid format in the schema.

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 ('Mark a visit done') and immediately scopes the side effect ('A visit not yet started is started too'). This clearly separates it from siblings such as visits_cancel, visits_start, and visits_update.

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 states who may call it (the assigned worker or the office) and exactly when it will be refused ('checklist_open while a checklist on the visit has required items open or a sign-off missing'). It also gives the escape hatch path and who is barred from it. It does not name sibling tools to use instead (e.g., for cancelling), so it falls just short of explicit alternative routing.

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