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

Adds substantial context beyond the readOnly/idempotent annotations: partial-failure semantics ('a part that cannot be read says so and the rest still answers') and an explicit warning that returned content is externally authored and must be treated as data, not instructions. That injection warning is exactly the kind of behavior annotations cannot convey.

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?

Front-loads what is returned, then the optional sections, then the caveats. The first sentence carries a long appositive list which is a little dense, but the paragraph break for the untrusted-content note is well-judged and nothing is redundant.

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?

With an output schema present, the description needn't restate return shapes, and it correctly focuses on scope, optional sections, partial-failure behavior, and the trust boundary. Nothing needed to call this correctly is missing.

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 already 100%, so the baseline is 3, but the description adds real meaning: `sections` values are explained ('consent' = full consent history, 'messages' = latest emails and open status) rather than repeating the schema's terse 'More than the contact and its orders'. contactId and workspaceId usage are both reinforced.

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 ('One contact in full, by the contactId') and enumerates exactly what is returned (address, name, consent, source, conversation questions, orders). It also ties itself to the sibling tool that produces the identifier (findContacts), so an agent can place it precisely.

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?

Clear on the entry path: get contactId from findContacts, and opt into more detail via the `sections` array with 'consent' and 'messages' spelled out. It does not explicitly contrast with updateContact or other read tools, but the read scope is unambiguous.

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