Corpus Deep Ask

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

With no annotations provided, the description carries the full burden and does well: it discloses the 30-120 s latency, the one-question-at-a-time constraint, and that the output carries [S1], [S2] source markers. It omits any statement about authentication, rate limits beyond latency, or cost, which keeps it short of 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?

Three short sentences, front-loaded with purpose, then output format, then caveats. Every sentence carries information; only the follow-up guidance could be considered optional.

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?

Because an output schema exists, the description need not explain return values, yet it usefully notes the source markers and how to resolve them via corpus_get_doc. For a slow, single-parameter tool with no annotations, latency, batching guidance, and follow-up are all covered.

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?

Only one parameter and schema description coverage is 100%, so the baseline is 3. The description reinforces the usage pattern ('one question at a time') but adds no semantics about question phrasing, length, or scope that the schema does not already 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?

States a specific verb+resource combination (LLM-assisted question answering) and a clear scope (the entire corpus, ~220K chunks) that distinguishes it as the 'deep' synthesis tool. It does not explicitly name the closest sibling (corpus_ask) or contrast itself with corpus_semantic_search, so differentiation is implied rather than stated.

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?

Offers useful operational guidance: 'Ask one question at a time' and a latency warning, plus a follow-up path via corpus_get_doc(doc_id). However, it never says when to prefer this over corpus_ask or corpus_semantic_search, which is the key selection decision for an agent facing these siblings.

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