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

Annotations cover the safety profile (destructiveHint=true, openWorldHint=true, idempotentHint=false), so the description's added value is the side-effect disclosure: the welcome-email flag causes SuiteDash to actually email the contact a portal invitation. It also explains the implicit company-creation behavior behind create_company_if_not_exists. Missing: whether duplicate contacts are merged/blocked and any auth/permission notes.

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 with no filler: write/identity first, requirements second, optional behaviors third, endpoint last. The 'WRITE:' prefix front-loads the most decision-relevant fact.

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 15-parameter mutation with a nested address object and free-form custom_fields, the description covers the required fields, the key conditional flag, and the risky side effect; the schema carries the rest. No output schema exists, and the description doesn't say what a successful create returns (e.g., the new contact ID), which is the main remaining gap.

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?

With 67% schema coverage, the description meaningfully supplements the schema by restating the cross-field dependency (email required unless role is Lead) and explaining how company_name pairs with create_company_if_not_exists. It leaves the remaining optional fields (tags, address, custom_fields) to the schema, which does describe them.

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?

Opens with a specific verb+resource plus a 'WRITE:' marker ('create a CRM contact in SuiteDash'), which immediately separates it from the read siblings (get_contact, list_contacts) and from suitedash_update_contact. The endpoint (POST /contact) reinforces exact scope.

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 real selection criteria inside the tool: email required except for Lead, link a company by name, and an explicit when-not ('leave send_welcome_email false unless the user asked for that'). It doesn't contrast against suitedash_update_contact or suitedash_create_company, so 4 rather than 5.

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