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

Beyond the annotations (idempotent, non-destructive, closed-world) the description discloses that no permissions actually change, who may invoke it, that self-escalation is blocked and the final lead cannot be removed, and that the feature is operator-gated. These are exactly the behavioral constraints an agent cannot infer from the structured fields.

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?

Four tight clauses with the purpose front-loaded ahead of authorization and gating details; no sentence is filler. Density is high but every clause carries new information, so it reads as efficient rather than bloated.

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 four-required-parameter mutation-prep tool with no output schema, the description covers purpose, authority, restrictions, and role-specific parameter guidance, while projectId and idempotencyKey semantics are handled in the schema. Only expectedRevision and the grants structure go unexplained.

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?

At 50% schema coverage, the description partially compensates by explaining that editors receive field scopeIds while reviewers require reviewScopeIds, adding value beyond the schema. It says nothing about the grants array shape or expectedRevision, so the remaining undocumented parameters are not covered.

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 states a specific verb (prepare) and resource (complete before/after dossier access list) and immediately clarifies 'No permissions change,' which distinguishes it from apply/confirm siblings. It does not name an alternative tool explicitly, so it stops short of a 5.

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?

It conveys when the tool is callable by stating authorization preconditions (current lead/delegated co-lead, or workspace owner/admin for legacy migration) and a feature gate ('disabled until operator acceptance'). However, it never routes the agent between this prepare step and apply_dossier_library_access / confirm_dossier_access, leaving the workflow position implied rather than stated.

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