check_compliance

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

Annotations cover readOnly/idempotent, but the description adds substantial context beyond them: fully offline, no network call, no API key, no credentials stored, no writes outside the process, regex match against bundled corpus, and explicitly does not classify risk tiers or call remote APIs. This is unusually rich disclosure that is consistent with the annotations.

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-loaded with the core action and the sibling exclusions, and nearly every clause carries operational value (offline guarantees, empty-input rejection, jurisdiction semantics). It is dense and slightly sprawling, but little of it is filler.

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 2-parameter read-only checker with an output schema, the definition supplies everything needed: input constraints, scope semantics, offline guarantees, and an explicit statement of return shape (PASS/FAIL with rule ID, severity, citation, remediation). No gaps that would cause a misinvocation.

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 already 100%, so the baseline is 3. The description still adds meaning beyond the schema: that GLOBAL is a separate corpus tag rather than the union of EU and US, that omitting jurisdiction evaluates the full corpus, and that the jurisdiction token should match the one used with list_rules.

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+resource (check already-produced text against TrustLint offline YAML rules) and explicitly positions it against siblings: 'not the hosted policy engine, not a system classifier' and 'for pre-generation screening of a prompt about to be sent, use scan_prompt.' An agent can distinguish it from scan_prompt and list_rules 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?

Explicit when-to-use ('post-hoc evaluation of text that already exists') and when-not ('for pre-generation screening ... use scan_prompt'), plus a note to reuse the same jurisdiction token as list_rules. Alternatives and the selecting condition are both named.

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