Suede Copy Check

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

Annotations already declare this read-only, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds real value beyond that by disclosing the output behavior — an A-F score with a finding per rule — and by naming the specific rule families applied. It still does not disclose scoring thresholds or limits (the 20000-character cap is only in the schema), but with annotations carrying the safety burden this is solid.

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 front-loaded sentence: purpose first, then the enumerated findings. No filler or repetition. The long rule list is dense but each item is load-bearing because it tells the agent what will be reported back.

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 three-parameter, non-destructive checking tool with a full output schema and complete annotation coverage, the description supplies what is missing: the scope of rules and the shape of the result. What it lacks is routing — no statement of how this differs from suede_copy_seo_audit or when another grading tool is the better call.

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. The description earns a bump by concretizing the houseStyle parameter — it spells out the actual house bans (em dashes, 'unlock', 'seamless') that toggling that flag applies — and by naming 'missing call to action' as a finding, which explains the role of primaryAction. It adds meaning rather than restating types.

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 description gives a specific verb and resource ('Check pasted copy against the pack's copy rules') and enumerates exactly what is scored: house bans, hedges, buzzwords, throat-clearing, passive voice, long sentences, reading grade, reader focus, and missing CTA. That is far more specific than the title. It does not explicitly distinguish itself from the closest sibling, suede_copy_seo_audit, so an agent must infer that this one covers style rules rather than SEO.

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 by the enumerated check types — an agent can infer this is the style/rules linter for a piece of copy. There is no explicit when-to-use or when-not-to-use statement, and no sibling is named as an alternative (e.g., when to route to suede_copy_seo_audit or suede_visibility_grade instead). The only routing hint lives in the schema ('pass false for another brand's copy'), not the description.

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