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

Goes well beyond the annotations: every run is held for admin approval regardless of connection settings, returns {status: 'pending_approval', approval_id}, consumes one included monthly Diagnostic before falling back to per-run prepaid billing or outright refusal, and billing mode is re-checked at approval with refusal on drift. Turnaround of 5–10 minutes is disclosed. It does not address what happens to duplicate submissions or how to cancel a pending run, which keeps it off a 5.

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-loaded with the core action and prior_diagnostic_id before the eligibility and billing rules. It is a single dense paragraph of long sentences; the permission and billing clauses are necessary but could be split into shorter statements for faster scanning.

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 mutation tool with 7 parameters, nested objects, no output schema and open-world/non-idempotent annotations, the description covers eligibility, mutation limits, billing, approval flow, expected latency and follow-up tools. An agent has everything needed to decide and call correctly.

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 a baseline of 3 applies, but the description adds real meaning: omitted side_a_scores and spend fields replay the prior run's values, and the approver sees each change beside the earlier value — a semantic the schema's "merged over the prior run's scores" only partly conveys. The billing note on which fields matter is useful context too.

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 ("Requests a new Diagnostic") plus the scope that separates it from its sibling start_diagnostic: it replays an earlier run's intake via prior_diagnostic_id rather than starting fresh. The immutable dimensions (website, business, account) are named explicitly.

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 layered when-to-use and when-not-to-use conditions: only on an admin-created Yellowhead connection explicitly allowed to make this request, never on an assistant sign-in connection, and only for accounts enabled for assistant-requested runs. It also names the wrong-tool cases indirectly (site/business/account cannot be changed here) and points to get_usage, get_approval_status and get_diagnostic for the surrounding workflow.

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