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

The annotations declare destructiveHint=true, but the description explicitly states 'Does not change access yet.' This directly contradicts the destructive hint, as the tool appears to only prepare a plan without mutating state. Per the rule, a contradiction with annotations warrants a score of 1. The description otherwise discloses behavioral traits (requires service account, review before applying), but the contradiction negates transparency.

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 compact and front-loaded with the purpose, then the behavioral details, then the requirement and the non-application statement. Every sentence earns its place, with no redundant or vague phrasing.

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 tool with 3 parameters, no output schema, and no nested objects, the description covers the purpose, the workflow (review before applying), the requirement for a service account, and the non-application nature. It does not detail success returns, but that is not necessary. However, the contradiction with annotations leaves a gap in behavioral context that completeness would require.

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?

The schema provides descriptions for projectId and idempotencyKey, but not for collectionIds. The description adds meaning by explaining that collectionIds represent the libraries to grant EDITOR access, and that an empty selection removes them. This fills the gap for the undocumented parameter, compensating for the 67% schema coverage.

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 the verb 'prepare' and the resource 'business libraries for a dossier', and explicitly distinguishes it from applying changes by noting 'Does not change access yet.' It describes the exact effect of the selection (replacing rights with EDITOR) and the role of an empty selection, making the tool's purpose unambiguous relative to siblings like apply_dossier_library_access.

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 provides clear context: it is a preparation step that requires review with the user before applying, and it mentions a requirement (dedicated service account). However, it does not explicitly name the alternative tool (apply_dossier_library_access) or list when not to use it, though the implication is strong. This is clear but not exhaustive.

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