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

Annotations are all false (readOnly, openWorld, idempotent, destructive), so they don't disclose side effects. The description compensates by disclosing that it 'may save a non-contact snapshot for 30 days and return plan_id,' that it does not confirm coverage or inventory, and that totals are estimates not quotes. It also explains status branches (plan, needs_roles, roles_not_found, city_not_found). This is rich behavioral context beyond annotations, and no contradiction exists.

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?

While lengthy, every sentence earns its place. The description is front-loaded with 'CALL THIS FIRST' and then enumerates return types, exclusions, alternatives, persistence rules, and status handling without redundancy. It is dense but structured, with no filler or repeated schema 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 complex tool with 6 parameters, an output schema, and 11 siblings, the description covers all important operational context: what the tool returns, what it doesn't do, when to call alternatives, side-effect behavior, and branching logic. The output schema exists, so return values need not be fully repeated, but the description still provides a high-level overview and action guidance on statuses.

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 description coverage is 100%, so the baseline is 3. The description adds minimal parameter semantics beyond the schema; it mentions 'Omit roles for the catalog and a suggested mix,' but the schema's roles property already says 'Omit to receive the role catalog and a suggested mix.' Other parameter details (city, date, headcount) are already fully documented in the schema, so the description doesn't add meaning beyond what structured fields provide.

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?

The description clearly states what the tool does: it returns a configured-market catalog match, role-level W-2 rate math, estimated totals, lead-time guidance, and compliance flags. It uses the specific verb 'plan' and resource 'staffing,' and distinguishes itself from siblings by stating 'CALL THIS FIRST for event staffing requests' and 'Use granular tools only for a single rate, date, or state fact.'

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?

Explicit guidance is provided: 'CALL THIS FIRST' establishes when to use, and 'Use granular tools only for a single rate, date, or state fact' names the alternative. It also gives a conditional instruction for persisting: 'If it returns no plan_id and the buyer needs persistence, call save_staffing_plan once; never save a plan that already has an ID.' Exclusions ('never accepts or submits contact details, reserves staff, or creates a quote request') further clarify boundaries.

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