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

With annotations only declaring readOnlyHint=false and destructiveHint=true, the description carries real behavioral weight: it discloses partial-update semantics, the side effect of batchId (deliberately moving a planned Work), the rule-checking pass against Batch rulesets during an active workflow run, and the refusal behavior when a Must rule fails. That is well beyond what the annotations convey.

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-loads the core purpose and the partial-update rule, then layers constraints. The final sentence about Batch ruleset validation is information-dense and takes parsing, but every clause carries distinct, non-redundant information, so nothing is padding.

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 7-parameter mutation tool with no output schema, it covers partial updates, the status constraint, batch movement, and rule-refusal behavior. It omits what a successful call returns and how label/size changes interact with downstream state, but the critical call-time risks are addressed.

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%, establishing a baseline of 3, but the description adds meaning the schema lacks: the const-constrained status is explained by intent (rewind a started Work to the queue) and batchId is clarified as a deliberate move of a planned Work. It just stops short of describing the title/description/labels/size update nuances.

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 ('Edit a Work's planning details') and immediately frames the scope as partial-update ('Only supplied fields change'). It distinguishes itself from the sibling mutators begin_work and finish_work by explicitly declaring that those are the only paths by which a Work starts or finishes.

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?

Explicitly routes the agent: status here only accepts 'planned' to send a started Work back to the queue, while starting and finishing go through begin_work and finish_work respectively. This names the alternatives and the exact conditions that select them rather than leaving routing to inference.

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