research

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

Without annotations, the description carries the full burden. It states 'read-only mode and report findings', implying no side effects, and recommends a timeout. However, it does not disclose timeouts, error handling, what constitutes a 'report', or how results are structured (output schema exists but not described).

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?

The description is concise at two sentences but lacks structure; it frontloads purpose but omits parameter guidance. Every sentence serves a function, yet more detail on parameter usage would improve utility without adding excessive length.

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?

Given 8 parameters (many optional), low schema coverage, and no annotations, the description is incomplete. It does not explain how parameters interact or when to use optional fields, leaving significant gaps for correct invocation. Output schema exists but is not described.

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 only 13% (low); only 'repo_root' has a schema description. The description does not explain the meaning or usage of the other 7 parameters (e.g., 'files', 'model', 'reasoning_effort'), failing to compensate for the low coverage.

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 clearly states the tool's purpose ('Investigate code, docs, and context in read-only mode and report findings') with a specific verb and resource. It distinguishes from siblings like 'build' or 'review' but does not explicitly differentiate from similar analysis tools like 'brainstorm' or 'reverse_engineer'.

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?

The description provides a recommended timeout ('20 minutes (1200s)') but offers no guidance on when to use this tool versus alternatives, no when-not-to-use conditions, and no mention of prerequisites or selection criteria among siblings.

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