quality_check

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

readOnlyHint=false is consistent with gates that may execute builds and tests, and the description reinforces this by noting a docs task can skip the build and test gates. It does not state what gets executed, whether failures abort or are reported in-band, or what side effects occur in the workspace, so important behavior for a non-read-only tool is left implicit.

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?

Three dense sentences with the core action front-loaded and the parameter modes packed into a single compact block; the parenthetical example earns its place. Slightly terse for the amount of conditional logic it encodes, but nothing is wasted.

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?

There is no output schema, yet 'return a compact JSON report' is never elaborated: the agent cannot tell what the report contains, whether pass/fail is signaled in the report or via an error, or how gate definitions relate to results. For a two-parameter tool with no annotations beyond readOnlyHint=false, that return-value gap is the main missing piece.

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 0%, so the description carries the full burden and does so for both parameters: 'checks' is defined by its default behavior (omit it and every gate runs) and 'task' is defined both semantically (only that task's profile gates) and syntactically (task=<id>). The only gap is what valid gate names look like beyond the pointer to taskgate.toml.

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 plus resource ('Run quality gates and return a compact JSON report') with extra scope detail: gate names come from [quality] in taskgate.toml and a built-in 'tasks' gate exists. It does not, however, distinguish itself from the sibling task_validate, which sounds like a close neighbor, so an agent must infer the boundary.

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?

The description explains the alternate modes ('without checks every gate runs; with task=<id> only that task's profile gates run') and gives a concrete example (a docs task can skip build and test gates). But this is parameter-selection guidance rather than when-to-use-this-tool guidance; it never says when not to run quality_check or when task_validate is the better call.

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