Corpus Ask

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

No annotations are provided, so the description carries the full disclosure burden. It does add genuine behavioral context: latency expectations (~2-10 s) and the presence of a confidence value plus cited chunks. However it says nothing about auth requirements, rate limits, corpus scoping, or what happens on a low-confidence/no-match result.

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 tight sentences with the core purpose and latency front-loaded and the alternative routing placed second. No filler, though slightly less compact than a single sentence that would still convey the same content.

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 return values need not be explained, and the description still gives a useful preview (confidence + cited chunks). For a single-param read/query tool this is nearly complete; only the relationship to the other corpus retrieval siblings is left unaddressed.

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?

One parameter with 100% schema coverage, so the schema already documents the 'question' argument including an example. The description adds no syntax, length, or formatting guidance beyond what the schema provides; baseline 3 applies.

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 and resource ('LLM-grounded answer over the corpus') plus the output shape ('short synthesized answer with a confidence value and the cited chunks'), and explicitly names corpus_deep_ask as the contrasting sibling. An agent can distinguish it from corpus_search and corpus_semantic_search without opening a 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?

Gives a clear positive case (quick answer) and an explicit alternative with its selector condition ('For deep multi-source research with [S1][S2] citations, use corpus_deep_ask instead'). It does not distinguish against corpus_search / corpus_semantic_search, which are the other plausible choices, so it stops short of full when/when-not coverage.

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