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

Annotations only say the call is a non-read, destructive, idempotent, closed-world write. The description adds real substance beyond that: partial-update semantics ('Only the fields given change'), visibility behavior ('A task the person cannot see reads as not found'), workspace reassignment/reprioritization floors, a contract lock on locked lines, and that the response carries prior values usable as an undo. This is exactly the behavioral context annotations cannot express.

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-loaded with the core action and its field list, then rules, then examples; each sentence is doing work. Slightly long and the closing example sentence is more motivating than strictly necessary, but nothing is egregiously wasteful.

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 an output schema present, return shape need not be spelled out, yet the description still notes that prior values are returned as the undo call. Given the tool's complexity (9 params, mutation, destructive hint), it covers visibility, locks, partial updates, reassignment rules, and undo — the agent has everything needed to call it correctly.

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% across 9 parameters, so the schema already documents every field, including the assignee/assigneeRef mutual-exclusion and the assigneeRefs set semantics. The description reinforces 'only the fields given change' and the undo-ref form, but adds little syntax or meaning the schema does not already carry; baseline 3 is appropriate.

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 ('Changes one task') and enumerates the mutable fields (status, due date, priority, title, assignee), so an agent immediately knows the scope. It scopes to a single task, implicitly separating it from list_tasks/create_task/delete_task, but never names a sibling or states its boundary against them explicitly.

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?

Gives concrete usage triggers via natural-language examples ('mark the drainage memo done', 'push the survey task to Friday'), which tells the agent when this tool applies. However, it offers no exclusions or alternatives (e.g. when to prefer update_time_entry or delete_task), so the routing guidance is context without contrast.

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