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

The annotations are minimal (readOnlyHint=false, openWorldHint=false, destructiveHint=false), so the description carries the burden. It adds significant behavioral context: updates are atomic and reviewed, permission-aware behavior, null clears a field, and the semantics of baseCommitId. This goes beyond the schema and gives the agent a solid understanding of side effects and preconditions. Slight deduction because it doesn't explicitly state the potential for partial failure or rollback behavior, but the atomicity mention covers most of it.

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 well-structured: it opens with a brief purpose statement, then covers usage preconditions (playbook search), constraints, key behavioral rules (atomic merge, partial updates, null clearing), and specific parameter scenarios. Every sentence adds value, and the information density is high without redundancy. The most important details are front-loaded.

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 complexity (9 parameters, nested updates object, permission-aware behavior) and the lack of an output schema, the description covers the key aspects an agent needs: prerequisites (playbook search), constraints (active records, same base, unique recordIds), merge semantics, permission handling, and parameter usage. It doesn't specify the return format, but since there's no output schema, a brief mention of the ChangeRequest object would be helpful. However, the description is comprehensive enough for safe invocation, so a 4 is warranted.

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?

The schema has 100% coverage with detailed descriptions for each parameter, so the description doesn't need to repeat them. It does add value by explaining the batch semantics of the 'updates' parameter (partial updates, null clears, each recordId appears once) and the purpose of baseCommitId, requireReview, and autoMerge in the context, which the schema descriptions don't fully capture. This elevates the score above baseline 3.

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 proposes partial updates to many records within a single ChangeRequest, which is a specific verb and resource. It distinguishes itself from related tools like records_create_bulk_change_request and records_create_change_request by emphasizing the 'partial' nature of updates and the batch aspect, making it clear this is for multi-record partial updates.

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 provides good usage guidance: it explicitly says to call playbooks search first if a playbook may exist, and it clarifies the constraints (all updates must target active records in the same Base, each recordId may appear once). It also explains when to use baseCommitId and requireReview, giving clear conditions. However, it doesn't explicitly state when NOT to use this tool versus alternatives (e.g., for single records or full updates), but the purpose is clear enough that the agent can infer.

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