Legal Render

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=true, openWorldHint=false. The description adds genuine extra context: the conditional 'keeping or dropping the HealthKit block' behavior and the 'local writes only' scope. It doesn't say what gets overwritten or whether existing files are preserved.

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 short, front-loaded lines covering purpose, usage, and return shape with zero filler. Every sentence earns its place.

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?

An output schema exists, so the description needn't restate return values (it does anyway, harmlessly). For a moderate-complexity local write tool with full annotation and schema coverage, it is nearly complete, only missing overwrite/behavioral detail on existing files.

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% and both parameters are documented in the schema, so the baseline is 3. The description doesn't add syntax or format detail for `values` or `app_dir` beyond what the schema already provides.

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 ('Fill') and concrete resources (store/privacy/*.md, backend/PRIVACY.md) sourced from spec and config. It clearly differs from siblings like legal_check/legal_verify, though it doesn't explicitly name them.

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 an explicit temporal trigger ('Use when: before legal_check') and a scope note ('Local writes only'). It does not explain when NOT to use it or contrast with legal_verify, so it falls 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.