proj_lint

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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false), so the added value here is the operational context: the analysis is deterministic and offline, and interface_contract results are downgraded to info rather than error when the interface or base lives in a library. That severity nuance is genuinely useful and is not derivable from annotations or schema.

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 core purpose is front-loaded in the first clause, and the long rule inventory is dense but each named rule helps an agent judge whether this tool will surface what it needs. The parenthetical and semicolon-heavy structure makes it read as a spec dump rather than a summary, costing some scannability.

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?

An output schema exists, so return-format detail is unnecessary, and the description covers scope, rule coverage, determinism, and the compiler-authority caveat. The remaining hole is the undocumented semantics of the `prefixes` map and the null/whole-project behavior of `name`, which an agent needs to call 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 description coverage is 0%, so the description has to carry all three parameters. It explains `rules` as a subset filter and gestures at `prefixes` as an 'override map', but never states the map's key/value shape (naming category to prefix list), and `name` is only implied by 'one object or the whole project' with no note that null means whole project. It partially compensates for the coverage gap without fully closing it.

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 and resource ('static checks over one object or the whole project') and then enumerates the exact rule classes it fires, from unused locals to FB_init SUPER^. It also draws the boundary against the authoritative sibling analyzers (xae_build + xae_diagnostics), so an agent can place it among the proj_* tools without opening a schema.

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?

'Deterministic and offline; the compiler (xae_build + xae_diagnostics) stays the authority' gives a clear when-to-use posture versus the build-based tools, and 'rules= subset to run' tells the agent how to narrow scope. It does not state sequencing (e.g., run before committing or before xae_build) or exclusions, so it stops short of explicit when-not guidance.

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