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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=false), it discloses non-obvious behavior: partial-update semantics, field-level authorization tiers, atomic all-or-nothing refusal on unauthorized fields, and that the response returns the updated value. None of this is derivable from the annotations.

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 patch-scope rule, followed by the permission rule and the read-first/return-value note. Dense but every clause carries load; minor density cost given how much it compresses.

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 28-parameter mutation with no output schema, the description covers the essentials: partial update, authorization, atomic refusal, and the returned value. It stops short of detailing per-field constraints, relying on the schema for those, which is a reasonable division given 54% schema coverage.

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 54%, but the schema already marks each sensitive field 'Owner only' and the description adds the crucial cross-cutting rule that unsent fields are left unchanged and that a mixed request is refused as a whole. It groups sensitive fields (contact email, bank, tax, invoicing) rather than re-documenting each of the 28, which is appropriate but leaves some gap on the unlabeled fields.

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 company details') and immediately adds scope in the form of PATCH semantics ('only the fields sent change'). It also names its read counterpart ('its read tool') so an agent can tell update_company apart from get_company without opening either 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?

Explicitly routes usage: read the current value first, then call this. It also states a concrete permission model -- any member may edit the public profile while contact email, bank, tax and invoicing are owner-only -- and that an unauthorized request is refused whole. When-to-use, prerequisites, and the failure condition are all given.

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