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

Annotations cover the safety profile (readOnly=false, idempotent=true, destructive=false), and the description goes well beyond them: undefined labels return 400, changing status overwrites percentComplete, the finished status always forces 100, and the task is returned post-reconciliation. That is exactly the side-effect information an agent needs before mutating progress data.

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 critical guidance (call list_task_statuses first, status overwrites percentComplete) is front-loaded, but the closing "Reconciliation:" paragraph restates the overwrite/update_task/finished-status rules almost verbatim from the preceding sentences, wasting space without adding information.

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 two-parameter mutation with no output schema, the description covers the return value ("Returns the task after reconciliation"), the validation failure mode, the permission boundary, and the progress side-effect — nothing an agent needs in order to call it correctly is missing.

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% and the status parameter's schema description is a near-verbatim copy of the prose, so the description adds little that the schema does not already carry. Baseline 3 applies when the schema does the heavy lifting and the prose merely mirrors it.

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+resource ("Set a task's status") and immediately scopes it to workspace-defined labels, which distinguishes it from the neighbouring set_task_progress and update_task tools. An agent can identify the operation and its constraints without opening the schema.

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 tells the agent to call list_task_statuses before setting a value, and names update_task as the alternative when the progress side-effect is unwanted. It also states a when-not condition indirectly via the Guest permission note and the 400 rejection rule.

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