dead_code

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive. The description adds that it returns CANDIDATES not a delete list, and discloses limitations (missing dynamic dispatch, reflection, cross-repo callers). This adds value beyond annotations.

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 (three sentences) with no fluff. It front-loads the core purpose and immediately follows with critical context (exclusions, limitations, usage guidance). Every sentence serves a clear purpose.

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?

Despite having 6 parameters and no output schema, the description is highly complete. It explains what the tool returns (CANDIDATES), what it excludes, its limitations, and how to use it properly (verify with impact calls and name search). This provides sufficient context for an agent to invoke it correctly.

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 100%, so baseline 3. The description hints at the 'kinds' parameter ('Lists functions/methods (optionally types/vars)') but does not elaborate beyond the schema descriptions. It adds no new semantic detail for other parameters like top_k, format, include_tests, or include_exported.

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 finds symbols not referenced in the indexed graph, listing candidate dead code. It specifies the symbol kinds (functions/methods, optionally types/vars) and exclusions (entrypoints, tests, HTTP handlers). The verb 'find' and resource 'dead code' are precise and distinct from sibling tools.

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?

Explicit guidance is provided: 'Use before a cleanup pass; confirm each with impact(upstream) + a name search first.' It also explains limitations (dynamic dispatch, reflection, cross-repo callers) implying when not to rely solely on the tool. It does not explicitly compare to sibling tools but the context is clear.

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