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

Annotations only supply the safety triad (readOnlyHint=false, destructiveHint=false, openWorldHint=false); the description carries far more: versioned publish semantics, preservation of layout and comments, all-or-nothing atomicity ("All ops apply or none"), and optimistic concurrency ("an op on something changed since base is refused"). That is exactly the mutating-and-recoverable behavioral profile an agent needs before writing.

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?

Two tight sentences plus a closing constraint, front-loaded with the action and its versioning outcome. The telegraphic style ("answers what changed, what breaks, new errors") is dense but never padded; nothing needs to be cut.

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?

With five parameters, no output schema, and a nontrivial atomic-plus-conflict-check mutation model, the description covers the essentials: versioning, preservation of untouched content, atomicity, conflict refusal, and the shape of the answer. Gaps are minor: dryRun and the note/History parameter go unmentioned, and there is no note on required permissions.

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 100% and the schema already documents doc/base/note/dryRun and lists the op shapes, so the baseline of 3 applies. The description adds no syntax or constraint information beyond restating that base is the version you read; notably dryRun is never referenced in the prose even though the description otherwise leans on the read-then-write workflow.

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?

"Changes an OpenAPI doc read at \"base\" and publishes the next version" is a specific verb+resource+lifecycle statement, and the answers clause ("what changed, what breaks, new errors") clarifies what the call produces. It is clearly distinct from generic editors in the sibling list (edit_doc, edit_db), though it never names an alternative outright.

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?

"read at \"base\"" implies a read-then-edit sequence, and the refusal-on-conflict sentence tells the agent to re-read when the doc moved underneath it. But there is no explicit routing: no statement of when to use this versus get/read/publish/apply, and no mention of when dryRun should be preferred.

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