check_composition

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

Annotations only say readOnly/openWorld=false; the description goes well beyond that by disclosing that 'the whole composition is checked and remembered' and that the time range only narrows returned findings. It also scopes what is validated ('Project data only — text extents are estimated'), which is exactly the kind of caveat an agent could otherwise misread as a bug.

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?

Front-loads the action and rule source, then severity semantics, then caveats, then timing advice — a sensible order. The inline return-shape snippet is dense but earns its place since there is no output schema; a slightly lighter rendering would read better.

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 supplies the return shape, severity taxonomy with required agent behavior, scope limitations, and invocation timing. Nothing an agent needs to call and act on this tool correctly is missing.

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 baseline is 3, but the description adds real meaning: t_start_us/t_end_us do not scope the check itself, only which findings are returned. That stateful nuance is not in the schema wording ('Only findings overlapping from here').

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 — checking a composition against craft rules and project taste — and names the concrete source of truth (skill craft/rules.md). No sibling tool does validation, so the role is unambiguous against the surrounding edit/restyle/motif tools.

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?

Gives explicit timing: 'Run it after your edits and after fixing,' and the severity definitions tell the agent what to do with each outcome (hard = fix before handoff, warning = fix or leave a tack, review = confirm). No explicit when-not-to-use or named alternative, which keeps it short of a 5.

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