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

With no annotations supplied, the description carries the full burden and does a fair job: it discloses the playbook-driven refusal, the error code, the accepted pointer formats (file:, storage:, PR URL), and that the result carries org + bound. It omits reversibility (whether a closed item can be reopened) and any permission/auth requirements.

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 paragraphs, front-loaded with the action and followed by the constraint; nothing is wasted. The reST double-backtick markup adds a little visual noise for an agent reader but does not obscure meaning.

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 three-parameter mutation tool with an output schema covering return values, the description supplies the one non-obvious behavior — the artifact precondition and its failure mode. Remaining gaps (reopen semantics, authorization) are secondary for correct invocation.

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 a 3. The description earns an extra point by resolving an ambiguity in the schema: work_status enumerates seven values, but the text states only done or cancelled apply here, which an agent could not infer from the enum alone. The agent identity override parameter is still unaddressed.

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 ('Mark a work item done or cancelled') and narrows the terminal states, which is more than a restatement of the name. It does not, however, distinguish itself from the sibling work_update, which an agent could plausibly reach for to change status.

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 artifact gate is explained well — done is refused with handoff_required until an artifact or pointer comment exists — which is genuine precondition guidance. But there is no explicit statement of when to choose work_close over work_update, nor when to prefer cancelled over done.

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