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

Annotations already carry destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the write profile is known; the description adds genuinely new context by clarifying PATCH-style semantics ('only the fields you pass are changed; nothing is cleared') and the failure mode for an unknown id. It also exposes the underlying endpoint (POST /customer/send), though it is silent on permissions or response shape.

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?

Four short sentences, front-loaded with the write nature and the update semantics; each sentence carries a distinct fact (verb/resource, partial-update behavior, precondition, transport). 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?

For a mutation tool with no output schema, the description covers the essential agent-facing facts: it is a write, it is a partial update, and it requires an existing id. The remaining gap is parameter-level documentation, which the low schema coverage leaves partially unaddressed.

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?

Ten parameters with only 30% schema description coverage, and the description documents none of them at the field level beyond restating that 'id' is a numeric identifier. The unlabeled fields (name, vat_number, contact_* ) rely entirely on self-explanatory names and maxLength constraints, so the description does not compensate for the coverage gap.

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 ('change fields of an existing customer'), adds the 'WRITE:' prefix that immediately separates it from the read-oriented siblings, and names the addressing key ('by its numeric id'). An agent can distinguish it from synchroteam_create_customer and synchroteam_get_customer without opening any 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 operating context: the id must already exist (unknown id fails) and only passed fields are changed, which is exactly what an agent needs to decide between a partial update and a create. It does not, however, name an alternative tool or state when to prefer create/get instead, 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.