detect_dead_code

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

No annotations exist, so the description carries the full burden, and it discloses almost nothing: it doesn't say whether the scan is read-only, whether it covers the whole project or a subset, how expensive it is on a large codebase, or what it returns. Only the scope 'unreferenced exports' hints that non-exported dead symbols are excluded.

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 front-loaded sentence with zero filler. It is efficient, though its brevity is partly under-specification rather than pure tightness.

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 annotations and no output schema, the description is the only source of behavioral information, and it omits the return shape (a list of symbol names? locations?), whether the result is exhaustive or heuristic, and any cost consideration for a whole-project scan. Complexity is low (0 params), but the disclosure gap is still meaningful.

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?

The tool takes zero parameters, so there is no parameter semantics for the description to explain; the baseline of 4 applies. Nothing in the description misleads about inputs.

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?

A specific verb ('Identify') plus a precise target ('unreferenced exports') scoped to the project. It is distinguishable from siblings like find_symbol or trace_dependencies by naming dead-code detection as its job, though it never explicitly contrasts itself with them.

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?

There is no statement of when to run this versus analyze_project, get_project_diagnostics, or trace_dependencies, nor any prerequisite (e.g., analyzed project state needed first). Usage is only implied by the word 'project'.

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