lint_workflows

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

With zero annotations the description carries the full burden and does so well: it declares read-only behavior explicitly ('Never modifies anything'), documents the suppression mechanism and its exact syntax, and states the shape of each finding (rule id, severity tiers, file:line including the exact line inside multi-line `run: |` blocks, explanation, fix). These are the behavioral facts an agent needs before deciding to run it in a pipeline.

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?

Purpose, severity model and read-only guarantee are front-loaded, which is good. But the middle is one very long sentence enumerating ~25 checks, several of which (cache keys, matrix size, unquoted 3.10) add little to an agent's decision to invoke the tool and could be compressed to a summary plus examples.

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?

For a read-only linter with an output schema already defined, the description covers scope, severity vocabulary, suppression, and a clear mutation guarantee. The one real hole is `path` semantics (what is scanned, recursion, default behavior), which is exactly the information 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% and the description never mentions the single `path` parameter — not whether it is a file, directory, or glob, whether traversal is recursive, or what the default '.' expands to. Given only one self-evidently named parameter, the omission is not fatal, but no meaning is added beyond the bare 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?

The opening sentence gives a specific verb and resource ('Lint workflows and composite actions'), names the exact rule set (33 rules, GHA1001-GHA1033), and the description scopes it clearly against siblings like fix_preview and pin_actions_plan by being purely diagnostic. An agent can distinguish it from every other tool in the list 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?

Usage is implied rather than stated: the long 'Covers:' list tells the agent what problems this detects, which implicitly tells it when the tool applies. However, there is no explicit when-to-use/when-not-to-use statement and none of the six siblings (e.g., fix_preview, pin_actions_plan) are named as follow-ups or alternatives, so routing is left to inference.

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