research

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

With no annotations, the description does real work: it declares the operation read-only, notes it is cheap, discloses data freshness ("reads the working tree, uncommitted changes included"), and describes the return shape with path:line refs and a confidence value. The remaining gap is latency/rate expectations and any limits on the number of distinct searches.

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?

Front-loaded with the core purpose, then the mechanism, then the return contract and a caution — a sensible ordering with almost no filler. The parenthetical about the working tree slightly interrupts the sentence flow but still earns its place.

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 no output schema and no annotations, the description covers what an agent actually needs: side-effect profile, tree freshness, return shape, and a reliability caveat. Cost and latency expectations for the "research worker" are the only meaningful omission.

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%, so the three parameters are already fully documented in the schema itself. The description adds only that a question is asked and that answers are short, without clarifying how `paths` scoping or `max_words` cap interact with the reported confidence. 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?

Opens with a specific verb+resource ("Find and explain code in this repository") and clarifies the mechanism (a read-only research worker answering a question). An agent can tell this is a code-lookup tool rather than a generic action tool, though it never contrasts itself with the ambiguously named `delegate` or `jobs` siblings.

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?

Use is implied by "find and explain code" and the closing instruction to "verify low-confidence answers before acting," which gives useful follow-up behavior. However there is no explicit when-not-to-use or which sibling to pick for adjacent tasks, leaving the agent to infer routing against `delegate`.

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