check_policy

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

With no annotations, the description carries the full burden. It explicitly states 'Report-only', which is a critical behavioral trait. It also discloses what gets flagged (GAs with domain mismatches, naming mismatches) and how the example profile is seeded (only mains that exist in the project are written). This covers the key side effects and constraints well, though it doesn't detail return format (but output schema exists).

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?

The description is moderately long but every sentence carries meaningful information. It front-loads the core purpose and then details parameters and side effects. It could be slightly more concise, but the structure is logical and the emphasis on key constraints (report-only, seeding) is effective.

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?

Given the tool has an output schema and two optional parameters, the description covers the essential behavior: what it validates, how to customize via profile_path, and how to generate an example. It explains the seeding nuance and the report-only nature. It doesn't elaborate on error handling or performance, but these are minor given the output schema and the tool's relative simplicity.

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 0%, so the description must fully explain parameters. It does: profile_path is described as a YAML profile path with an omission behavior (infer from project), and write_example_to is described as dropping a commented example profile seeded from the project's main groups. This adds substantial meaning beyond the bare schema.

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 clearly states a specific verb ('Validate') and resource ('loaded project against a Project Policy Profile'), and explicitly distinguishes it from a generic standard by emphasizing 'your agreed rules'. It also names the exact checks performed (main-group taxonomy, naming regex, exemptions), making it distinct from siblings like check_naming and check_secure.

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?

The description gives clear context on when to use the tool: when you have an agreed policy profile. It explains the optional profile_path behavior (omit to infer from project) and the write_example_to use case. It doesn't explicitly name alternative tools, but the purpose is specific enough that an agent can infer when not to use it. It lacks explicit 'use X instead' guidance, so not a 5.

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