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

Annotations only declare the safe read profile; the description goes much further by disclosing the response contract (`booked: false`, `mode: "deeplink"`), the handoff to third-party platforms, and explicit prohibitions against rendering it as a confirmation or claiming a table is held. This is exactly the behavioral disclosure annotations cannot carry.

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 core contract, then consequences, then fallback handling, in five tight sentences with no filler. Emphasis (ALREADY FILLED IN, DOES NOT, MUST NOT) is functional rather than decorative.

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?

With no output schema, the description fully compensates by specifying the returned fields, the non-reservation semantics, and the phone-number fallback path. Everything an agent needs to call and correctly represent the result is present.

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. The description adds one genuinely new fact — that party, date and time are already filled into the link — but gives no syntax or omission behavior beyond what the schema already documents.

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+resource (a booking page / deep link for one place) and immediately clarifies what it is NOT (a reservation, a held table). The agent can tell this apart from search_places or place_details without opening a 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?

Gives clear context for use (booking a specific place with party/date/time pre-filled) plus a branch when the venue has no platform (offer the returned phone number instead). It does not name a sibling alternative such as concierge_answer, so it stops short of explicit routing.

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