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

Annotations already declare readOnly, idempotent, and non-destructive, so the description only needs to add what the annotations cannot. It does so by enumerating the four actions the tool will not perform, which is the key routing risk for a scheduling-adjacent endpoint.

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 sentences, zero waste, with the positive purpose stated first and the scope exclusions immediately after. Every clause carries information.

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 one-parameter, read-only lookup with no output schema, the description covers what is returned (link and phone) and what it is not. Minor gap: it doesn't say whether the result is static or derived, but that is unlikely to affect 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 coverage is 0%, but there is a single parameter whose enum lists exactly one value, so the schema is effectively self-documenting. The description says 'selected office', which gestures at practice_id without explicitly tying the term 'office' to the 'practice_id' field name, leaving a small naming mismatch.

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?

States a specific verb and resource: returns the public scheduling link and phone for a selected office. This is clearly distinct from siblings like get_office_hours and get_practice_details, though it never names them explicitly.

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 second sentence draws an explicit boundary: it does not read availability, hold a slot, submit a request, or confirm an appointment, which steers an agent away from treating it as a booking tool. It stops short of naming the sibling tools that would handle those other tasks.

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