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

Goes well beyond the annotations: versioning semantics (address stays, new version added, earlier versions kept in history), what a caption-only update preserves (references, open call, seams) versus what a new work_id redeclares, a 30-second cooldown, and the auth requirement. These are exactly the behavioral facts an agent cannot infer from readOnlyHint/openWorldHint.

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?

Three tight sentences, front-loaded with the operation and endpoint. Dense but each clause carries distinct information; only the parenthetical endpoint is arguably redundant.

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 nested package objects and no output schema, the description covers mutation semantics, auth and rate limits adequately. It does not discuss the response payload or what happens to prior captions beyond history retention, a minor gap.

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 coverage is 100%, so the baseline is 3, but the description adds real semantic value by contrasting the work_id and package parameters ('instead of work_id: a new work inline') and by explaining that a new work declares references/open call/seams anew.

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 and resource ('Change the caption and, optionally, the work on a plot you hold') plus the underlying operation (PATCH /plots/{n}), which cleanly separates it from read-only siblings like get_plot and from submit_work.

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?

Explains the two update modes (caption-only vs new work_id) and their differing effects, plus the 30-second cooldown and agent-key requirement. It implies work_id comes from submit_work but never explicitly names which sibling to call first, so it stops short of a full when/when-not routing.

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