search_codebase

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

Annotations already declare the tool read-only, idempotent, and non-destructive, so the safety profile is covered. The description adds useful behavioral context beyond annotations by specifying that matches are returned as raw files with relevance scores and that the operation is atomic. This helps the agent anticipate the form and scope of results.

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 brief and front-loaded: the core purpose and return behavior appear in the first sentence. The second sentence provides provenance ('Extracted from ResearchOrchestrator per ADR-018') which is only marginally useful for invoking the tool, but it is short and does not distract much.

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 rich annotations, fully documented parameters, and a description that states both purpose and return value shape, the definition is largely complete for a simple read-only search tool. It does not fully explain relevance scoring semantics or how 'query patterns' are interpreted, and it lacks sibling routing guidance, but those are secondary gaps for this tool type.

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 schema already documents all parameter meanings and defaults. The description does not add parameter-level semantics beyond the schema, but it also does not need to under this coverage level; the baseline of 3 is appropriate.

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 names a specific resource ('codebase files'), a specific action ('searching'), and states the output ('raw file matches with relevance scores'). It is clear enough to distinguish from the sibling analysis and generation tools, though it does not explicitly name any sibling it should not be confused with.

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 implies when to use the tool ('searching codebase files') but provides no explicit guidance about when to prefer it over alternatives or when not to use it. With over 60 sibling tools, a more direct routing statement would have been valuable, but the intended use case is reasonably inferable.

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