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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial context beyond them: file contents are not sent back, secrets are scanned and can block, blocked results list file/line/kind, and hosted profiles are rejected with a specific error code. That is exactly the layered disclosure this dimension rewards.

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 trigger and the effect, and every sentence carries operational information (scan behavior, return payload, refusal code, no account). It is dense rather than padded, though the profile listing sentence is the weakest link since the enum is broader.

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 6-parameter tool with nested objects and an output schema, the description covers trigger, side effects, refusal path, return contents, and cost/auth posture. Return values need not be explained further because an output schema exists, so nothing essential 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 description coverage is 100% and every parameter, including the nested context object, is documented in the schema itself. The description adds only marginal value (mode defaults to bounty, the three core profiles), and it names fewer profiles than the enum actually contains, so it neither compensates for nor enriches the schema meaningfully. Baseline 3.

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 ('prepare a review', 'scans the files for secrets') and precisely distinguishes itself from run_review by explaining that hosted profiles are refused here with code hosted_profile. An agent can place it against its siblings without opening any 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 timing ('Call before reviewing code or a draft report with your own model'), an explicit alternative ('run it with run_review'), a pointer to list_profiles for the profile ids, and a stated precondition ('No account needed') plus the acknowledgeWarnings escape hatch. Nothing is left to inference.

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