Revise a Reference Recreation Plan

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

Despite annotations already marking the tool as not read-only, not idempotent, and not destructive, the description adds valuable behavioral context: it creates an immutable new revision (no in-place mutation) and invalidates previous approvals ('Any earlier approval becomes stale'). This goes beyond what annotations convey by explaining the concurrency mechanism and the side effect on approvals, which is crucial for an agent to anticipate outcomes.

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 two concise sentences with no filler. It front-loads the core behavior (creating an immutable next revision) and follows with the key side effect (approval staleness). Every word contributes meaning, and it avoids restating the schema or annotations.

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 (large nested plan schema, immutable revisioning, optimistic concurrency), the description covers the most critical behavioral aspects but leaves context gaps. It does not explain what happens on concurrency conflict, how the optional 'approved' parameter interacts with staleness, or the overall update workflow relative to other reference-plan tools. The detailed schema and output schema reduce the need to document return values or field structures, but the description still omits practical usage context.

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 0% and the description provides almost no parameter-level semantics. It implies expectedRevision relates to optimistic concurrency, but does not explain planId, plan, or approved. Parameter names are somewhat self-explanatory, but the optional 'approved' field's role in the revision/approval lifecycle is ambiguous from the description alone. The verbose schema constraints help validate input but do not convey business meaning.

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 tool creates a new revision of a reference plan, which matches the 'update' name via immutable revisioning. It distinguishes this from sibling tools like get_reference_plan or create_reference_drawio by focusing on revision creation rather than retrieval or file generation. However, it does not explicitly mention the optional 'approved' parameter or frame the action as updating an existing plan, which would strengthen clarity.

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?

No guidance is provided on when to use this tool versus alternatives. The description does not mention that this is the tool to call when modifying an existing reference plan, nor does it reference sibling tools like get_reference_plan for reading or prepare_reference_recreation for pre-update steps. The optimistic concurrency hint implies a precondition (expectedRevision must match current), but this is not elaborated or compared to other tools' workflows.

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