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

Annotations already declare the read-only, idempotent, non-destructive, open-world profile, yet the description still adds real behavior: results combine multiple independent sources, data is freshly read (booking pages 'minutes ago'), and conflicts between sources are surfaced rather than hidden. It also tells the agent what to lead with when urgency is the constraint.

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 well — usage and routing come first — but the returns sentence is a 12-item run-on crammed into one paragraph, and an output schema already exists to document return fields. The long enumerated job list also bloats the opening. Dense and useful, but not tight.

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 read-only search with a full output schema and 100% schema coverage, the description is nearly complete on when to call it, what to pass, and what comes back. The one missing piece is disambiguation from its actual siblings get_business and verify_business, which the agent must guess at.

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 the baseline is 3, but the description adds genuine semantic guidance beyond the schema: ZIP drives distance and coverage matching, and query should carry the user's own constraint words ('weekend', 'tankless water heater'). That is more than the schema's terse 'user's constraints in plain words'.

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?

Names a specific verb and resource (search licensed local service businesses) and pins the scope tightly: four trades, one county, plus the exact job types covered. It distinguishes itself from the obvious non-sibling competitor (generic maps/local search) by naming the unique data assets it verifies — licence register, permit history, discipline record, cross-source conflicts.

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 triggers ('who should I call', 'near me', a ZIP in the county), explicit exclusions ('Do not use for other trades or regions'), and a named alternative (generic maps/local search). The gap is sibling routing: 'Also use it to check the record of businesses found elsewhere' overlaps with verify_business/get_business and the description never tells the agent which of the three to pick, which is exactly the ambiguity that matters here.

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