flow

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

With no annotations, the description carries the full burden and does reasonably well: it names the emitted schema (ce.flow-report), states the tool is report-only, and discloses a real semantic trait — each finding is labeled judged or advisory, with unused parameters always advisory. It omits auth/permission requirements and execution cost, which are minor for a read-only analyzer.

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 dense, semicolon-chained sentence that is front-loaded with the core purpose but heavy with internal jargon ('judged by the core over flow/1', 'ce.flow-report schema') that costs reading effort. Information-dense and mostly earning its place, but readability suffers.

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, the description steps in by naming the report schema and the fields findings are placed by (path, unit, kind, lines, variable) plus the judged/advisory flag. Together with 100%-covered parameters, an agent has enough to call it correctly, though not enough to know exact output shape.

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 the two parameters (kind, path) are already documented and the baseline is 3. The description references placement by 'kind' and 'path' but adds no syntax, accepted values, or default semantics beyond the schema.

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?

States a specific verb+resource: detects dead code inside functions, then enumerates the exact classes (unreachable statements, dead stores, unused locals and parameters). The 'inside functions' scope implicitly separates it from the sibling deadcode tool, though the sibling is never named.

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 explicit when-to-use guidance, no prerequisites, and no routing to alternatives. 'Report-only' hints that it does not mutate, but the agent is left to infer when to pick flow over deadcode, scan, or structure on its own.

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