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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds real behavior: it discloses the response components and the important edge case that items above your visibility class return an account_required pointer rather than content. It does not cover cost, latency, or whether routing has side effects on the corpus.

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?

Two sentences, no filler, with the core action and the return shape front-loaded before the visibility-class caveat. Every clause carries information.

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?

With an output schema present, the description needn't enumerate return fields, and annotations carry the safety profile; what remains is a clear statement of what routing does and the account_required fallback. The only substantive gap is the undocumented domain parameter.

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 0%, so both parameters (task, domain with default 'general') are undocumented structured fields and the description must compensate. It says nothing about what form the task should take or what values domain accepts and how 'general' behaves, leaving the second parameter entirely opaque.

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 (route) and resource (a task to the best corpus item), plus what comes back (decision kind, picked item, score, citations). It is distinguishable from read-only siblings like corpus_item or read_corpus_item, though it never names search_corpus, the closest alternative, and 'Laya' is unexplained.

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?

Usage is implied rather than stated: the mention of 'decision kind' and 'score' suggests this is for choosing among candidates rather than fetching a known item, which points away from read_corpus_item. But there is no explicit when-to-use, when-not, or named alternative versus search_corpus.

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