corpus_search

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

With no annotations, the description carries the full behavioral burden. It does disclose the ranking behavior and that results are passages (best passage per page), which is genuinely useful. However, it says nothing about read-only safety, cost/latency over a potentially large corpus, pagination beyond k, or how ties/scores behave.

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?

A single well-formed sentence that front-loads the action ('Retrieve across the accumulated corpus') and then the mechanics and return shape. No filler, no redundancy.

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 spelled out, and the description is adequate for a simple 2-parameter read tool. The remaining gap is the absent differentiation from sibling retrieval tools, which matters given how many similar siblings exist.

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 coverage is 0%, so the description must compensate, and it partially does: 'natural-language query' clarifies the query parameter and 'top `k`' clarifies that k is the result count. It still omits max/min behavior for k, whether k is bounded, and any query syntax constraints.

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?

The description gives a specific verb chain (Retrieve/ranks/returns) and a clear resource (the accumulated corpus), plus the output shape (top k pages with their best passage). It distinguishes itself implicitly by being a natural-language ranking retriever, but it never names or contrasts the siblings (search, grep, corpus_list), so an agent must infer the boundary.

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 only implied: the phrase 'natural-language query' hints that this is for semantic/fuzzy retrieval rather than grep-style literal matching, and 'across the accumulated corpus' hints at corpus-wide scope. There is no explicit when-to-use/when-not guidance and no routing to search or grep, which are the obvious alternatives.

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