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

Annotations already declare non-read-only, non-destructive. The description adds real value beyond that: partial-update semantics ('only pass the fields you're changing'), the 409 failure condition, and the required NOMADSTAYS_MCP_AGENT_TOKEN auth. Doesn't describe response/return behavior.

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, front-loaded with the core action and scope, then the field-set rule, then the failure condition and auth requirement. No filler.

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?

Covers scope, partial-update semantics, auth, and error behavior, which is good for a mutation tool. But with 25 parameters and 20% schema coverage and no output schema, per-field semantics rely entirely on an external reference (createStayApplication), leaving the definition incomplete for such a wide parameter surface.

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 20% across 25 params, so the schema does not carry the burden. The description adds patch semantics and defers field detail to createStayApplication ('Same field set and validation rules'), which is a reasonable strategy but leaves most field meanings unstated in either place.

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 ('Update') and resource ('existing, not-yet-submitted Stay Application'), immediately distinguishing it from createStayApplication (create), submitStayApplication (submit), and getStayApplication (read). The partial-update nature is explicit.

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?

Clearly scopes usage to existing, not-yet-submitted applications and gives the when-not case ('Fails with a 409 if the application has already been submitted'). It references createStayApplication for the field set but doesn't explicitly name the alternative to use once submitted.

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