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

Annotations declare destructiveHint=true; the description adds the partial-update semantics ('Only provided fields change'), which is useful behavioral context. But it doesn't disclose reversibility, required auth scopes, or what happens for missing/invalid ids.

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 short sentences, front-loaded with the action and mutation semantics; nothing wasted.

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?

Adequate for a partial-update tool with full schema coverage and annotations, but for a destructive mutation it should say more about side effects, error handling, or return shape (no output schema).

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 schema already documents every parameter including the unusual extras passthrough and link-combination behavior. The description adds little param-specific detail beyond saying which fields change.

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 ('Update fields on an existing person'), distinguishes partial-update semantics ('Only provided fields change'), and names the underlying endpoint. Clearly differentiable from twenty_create_person and twenty_get_person.

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?

States context is an existing person and that it's a partial update, which implies when to use, but names no alternative (create vs update) and no prerequisites (permissions, existence of id).

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