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

Annotations declare destructive, mutating, and idempotent hints, but the description adds substantial context: preservation of untouched content, full revalidation, creation of a new immutable review subject, and explicit warnings about claiming approvals or widening the plan. This exceeds what annotations provide and gives the agent a clear picture of side effects and constraints.

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 three sentences of high-density information: action, behavior, constraints, and cautions. It front-loads the core purpose and wastes no words. Each sentence earns its place, and the structure is orderly—action first, then outcomes, then limits and warnings.

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's complexity (9 required params, nested objects, no output schema) and sparse schema coverage, the description only partially prepares the agent. It covers the replacement semantics and revision matching but omits how to obtain the required job IDs and hashes, what a 'persisted root' is, and what the resulting review subject entails. It's adequate for a niche tool but leaves notable gaps.

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 only 11% (only projectId), so the description carries the burden of explaining parameters. It mentions the replacement limit (at most 8) and the requirement to target the exact revision, but does not explain crucial fields like basis, expectedRevision, analysisRevision, idempotencyKey, or declaredProvenance, or how they relate to each other. This leaves the agent guessing about these nested objects.

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 action ('Replace at most eight explicitly named sections') against a precise target ('the exact current draft revision'), clearly naming the resource and operation. It also distinguishes itself from siblings like submit_draft by focusing on section replacement within a revision, making its purpose unmistakable.

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 implies usage for corrections but does not explicitly contrast with alternatives such as request_matrix_changes or submit_draft. It provides constraints (max 3 corrections, obtain arbitration after failures) but never says 'use this instead of X when Y'. It leaves the choice logic to the agent without explicit routing guidance.

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