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

Annotations only say this is a non-read-only, non-destructive write; the description adds genuinely new behavior: privilege requirement, mandatory justification, and the fact that changes are audited. It omits concurrency behavior (expected_version) and whether omitted fields are left untouched, which matter for a partial-update mutation.

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 compact sentences with the permission gate and the prohibited value front-loaded; nothing is padded or restated from the title.

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?

Output schema exists, so return values need not be described, but with nine parameters at 0% schema coverage and no enum on status, the definition leaves key semantics undocumentable from anywhere else. The unmentioned optimistic-locking parameter and the schema/description mismatch on 'reason' are the notable gaps.

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 0%, so the description carries the burden and does explain six of the nine fields, including the non-obvious 'reason is required' constraint. However, 'agent' and 'expected_version' are never mentioned and have no schema descriptions, leaving the agent to guess at their meaning; the 'reason' requirement also conflicts with the schema, where only task_key is required.

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?

Uses a specific verb (edit) plus the exact resource fields it can change (title, description, priority, assignee, status), so an agent knows this is a targeted mutation rather than a general one. It does not name which sibling to use for closing a task or for status-only changes, though the '(never DONE)' clause implies set_status covers that.

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 a hard precondition (SUPER_ADMIN only) and an explicit exclusion (status can never be set to DONE here), which steers the agent away from a common misuse. It stops short of naming the alternative tool for terminal status changes or describing what to do when the caller lacks SUPER_ADMIN.

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