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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=true, openWorldHint=true. The description adds meaningful behavioral context: it saves an unapproved candidate only, does not approve the original answer, replacements remain active until the new version is separately approved, and client identity is never inferred. This goes beyond the annotations and clarifies the mutation's 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 compact and front-loaded with the core purpose, followed by requirements and side-effect caveats. Every sentence adds information: immutability, source revision, prerequisites, explicit IDs, unapproved status, and replacement behavior. It is slightly dense but not 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 mutation tool with no output schema and a complex nested proposal object, the description covers the key workflow context: prerequisites, scope explicitness, unapproved candidate behavior, and replacement semantics. It doesn't describe the return value or error conditions, but the annotations cover idempotency and destructiveness. The main gap is the lack of detail on nested proposal fields, which the schema partially documents by structure but not by semantics.

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 67%: projectId and idempotencyKey have descriptions, but the proposal object and its nested fields (answerId, answerRevision, ownerUserId, scope, validFrom, validUntil, replaces, etc.) have no descriptions. The tool description adds high-level meaning about the proposal (requires proof, owner, bounded validity, explicit scope) but doesn't explain individual nested fields like claimVersionId, evidenceVersionId, or replaces. The description partially compensates but leaves the agent to infer the semantics of several nested parameters.

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 ('Propose') and resource ('an immutable reusable answer from the exact source revision'), and clarifies it saves an unapproved candidate without approving the original answer. It distinguishes itself from approval/promotion siblings by emphasizing 'unapproved candidate only', though it doesn't name a specific sibling tool.

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: requires a current reviewed proof, owner, bounded validity, explicit reuse scope, and explicit IDs with no client identity inference. It implies this is the proposal step before approval, and contrasts with 'without approving the original answer' and 'until this new version is separately approved', which tells the agent when to use it versus approval tools. It doesn't explicitly name alternatives, but the workflow position is clear.

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