Resolve a task to the one best Agent402 tool

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

Annotations already carry the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description adds value where it matters: it discloses the return contract ({ task, matches } with top pick first) and the required next action, and signals deterministic decision behavior rather than exploratory search. No contradiction with annotations. It doesn't cover no-match or error behavior, but the core behavioral traits are disclosed.

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?

Three sentences, each earning its place: purpose plus behavioral contrast, usage condition, and return format plus next step. The key instruction is front-loaded, and the only slightly redundant detail ('hosted /api/find resolver') does not bloat the definition.

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?

An output schema exists, so the description rightly skips re-explaining return values; annotations cover the safety profile. It completes the agent workflow by stating when to prefer this tool and what to do with the result (invoke catalog.call). Residual gaps such as behavior when no tool matches or how the limit affects ranking are minor given the simplicity of the tool.

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% (both 'task' and 'limit' have descriptions with examples), so the baseline of 3 applies. The description adds only marginal semantic context — the phrase 'with the chosen slug + params' reinforces the task→tool resolution mapping but adds nothing about the limit parameter or format requirements beyond the schema.

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 decisive behavioral contrast ('DECIDE, don't browse') and states a specific verb+resource: resolving a plain-language task to the single best-matching Agent402 tool via /api/find. It also positions itself in the workflow by naming catalog.call as the follow-up, so an agent can distinguish find from the catalog.search and route_and_execute siblings without opening their schemas.

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?

'Prefer this for anything outside the flagship list' is an explicit when-to-use condition, and 'don't browse' warns against substituting a search/browse workflow. The follow-up 'then run catalog.call' routes the agent to the next step, though it never names the siblings it competes with or states the explicit when-not case (e.g., 'if you already know the tool, skip this').

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