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

Annotations only declare destructiveHint=true, so the description carries the rest: it warns that workflow automations may fire (side effects beyond the record itself) and flags validation coupling to account settings, which prevents failed calls. It stops short of describing permissions/token scope or what the response contains.

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 purpose and the mandatory-input rule, then validation, then side effects, then the API endpoint. Every sentence earns its place with no repeated or filler content.

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 23-parameter mutation tool with no output schema and only a destructiveHint annotation, the description covers identity requirements, required enums-like fields, external validation, and automation side effects. It omits what is returned (e.g., new contact id) and any duplicate-detection behavior, which keeps it just shy of complete.

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 100% schema coverage the baseline is 3, but the description adds a constraint the schema cannot express: the 'at least one of first_name/last_name/display_name/company' identity rule, plus the meaning of record_type_name as a workflow and status_name as a status within it. That is genuine added value over the minLength-only schema entries.

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 ('Create a contact') and pins the underlying operation ('JobNimbus: POST /contacts'), so it is immediately distinguishable from the create_job/create_note/create_task siblings. No ambiguity about what the tool produces.

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 preconditions: at least one identity field (first_name/last_name/display_name/company), plus required record_type_name and status_name that must match account settings, with an explicit pointer to jobnimbus_get_account_settings. It does not, however, contrast with jobnimbus_update_contact (i.e., when to create vs. modify), so it falls short of full when/when-not coverage.

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