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

Annotations already declare readOnly=false, idempotent=true, destructive=false. The description adds meaningful behavior beyond that: 'This saves a proposal only' establishes that it persists a draft rather than finalizing, and 'expectedRevision implements optimistic concurrency' discloses the concurrency-failure model. It does not describe return values, but adds real context over the structured hints.

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?

Front-loaded with the core purpose, then the action mapping, then the crucial 'saves a proposal only' caveat. Sentences are dense but each carries weight. Slightly packed with multiple concerns in one block, but nothing is wasted.

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?

There is no output schema, and the input schema is deeply nested with 5 required params. The description covers the item-action semantics well but leaves the analysisRevision/expectedRevision relationship, idempotencyKey reuse, and response behavior unexplained, so an agent is not fully equipped for a complex mutation.

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 40%, so the description should compensate. It does explain the critical action enum values (fill_existing, create_new, attach_existing, reference_only, request_missing) and states that language and rationale are required per item, and touches expectedRevision. But it leaves plan, analysisRevision, idempotencyKey, and projectId essentially undocumented beyond the 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?

States a specific verb+resource: 'propose the complete sourced multi-document plan' triggered 'after RFP analysis'. It clearly reads as the proposal-authoring step and hints at its counterpart ('before requesting agreement'). However, it does not explicitly name how it differs from sibling read_document_plan or request_plan_agreement, so sibling differentiation is only implicit.

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?

Provides a clear trigger condition ('after RFP analysis') and a sequencing rule ('present it to the user before requesting agreement'), which routes the agent to request_plan_agreement rather than calling it blindly. It also gives when-to-use guidance for the action variants. It stops short of explicit when-not-to-use or a named alternative tool.

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