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

Adds real behavioral context beyond the destructiveHint annotation: partial-update semantics, an immutable field (listing), an explicit statement that cancellation and repricing are out of scope, and a non-obvious warning that channel-driven date changes may be overwritten. It omits permission/auth requirements and any indication of what the response contains, so it is not a full 5.

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 tight sentences plus the endpoint reference, with the core action and the most important constraint (partial update) front-loaded. Every sentence carries a distinct fact: scope, patch behavior, restrictions/caveats.

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 25-parameter mutation tool with no output schema and only destructiveHint for annotations, the description covers scope, partial-update behavior, and the key traps (immutable listing, channel overwrite). What remains thin is error/permission behavior and confirmation of what a successful partial update returns, which 25 params of write surface would benefit from.

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 already 100%, so the baseline is 3, and the description earns an extra point by clarifying patch semantics (only send changed fields) and by stating that listing cannot be modified, which constrains what the caller should pass. It does not explain field interactions (e.g., adults/children vs numberOfGuests, arrival/departure pairing).

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?

Specific verb + resource ('Change fields on an existing reservation') followed by an enumerated scope of what can be changed (guest details/counts, dates, check-in/out hours, door code, notes). It explicitly separates itself from create_reservation ('existing') and from cancel/repricing tools, so an agent can place it without opening the 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 patch semantics ('Send only the fields to change') plus explicit exclusions ('the listing cannot be changed', 'never cancels or reprices a booking') and a caveat about channel overwrites. It stops short of naming a sibling tool to use for the excluded operations (cancellation/repricing), so 4 rather than 5.

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