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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds real behavioral context beyond them: unauthenticated calls return only public data, cards are visibility-filtered per viewer, and card text is third-party content to be treated as data (a clear prompt-injection boundary). It also discloses the 20-per-page cap. Missing only rate-limit or empty-result behavior, so a 4 rather than 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?

Purpose is front-loaded, followed by access constraints, then sibling routing — a sensible order with no filler sentences. It is dense and packs several distinct ideas into one paragraph, but each sentence carries information the agent needs.

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?

This is a complex tool (9 params, nested criteria, trust thresholds) with no output schema, so the description carries extra burden. It hints at the return shape ('cards', page cap) but never explains cursor pagination, how to resolve category/region terms (the sibling search_term/party tools exist), or how criteria combine with free-text 'text'. Adequate but with clear gaps for a tool of this depth.

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 schema coverage at 44% across 9 parameters, the description compensates only partially: it explains the three 'target' values and the page-size ceiling (matching limit's maximum of 20), but says nothing about sort, kinds, cursor, min_trust, party_kinds, or how criteria codes should be resolved. The nested criteria object is left entirely to the schema's own field descriptions.

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 (find) and enumerates the three searchable resources with parenthetical definitions (offerings = products/services/rentals/jobs/partnerships, needs = what others look for, parties = companies and people), which map directly onto the 'target' enum. An agent can distinguish this from save_offerings, save_need, and start_interaction without opening any schema.

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?

Explicitly routes to alternatives with conditions: 'publish a need with save_need instead of repeating searches' and 'to ask, get a price, order or book, use start_interaction with the offering_id'. It also states the anonymous/no-login condition that changes result scope, so both 'when to use' and 'when not to use' are covered.

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