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

Annotations are minimal (readOnlyHint=false, destructiveHint=false), so the description carries the full behavioral burden, and it excels. It explicitly discloses that 'assignees' REPLACES rather than appends, that omitting it leaves assignees untouched, that an empty list is refused with the rationale (Matrix rejects unassigned tasks), and that priority/status are case-insensitive. These are exactly the non-obvious behaviors an agent needs to avoid destructive mistakes.

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 description is front-loaded with purpose, then dedicates each subsequent sentence to a distinct behavioral fact. No sentence is redundant; the assignee warning is complex enough to justify its length, and the closing rationale for the empty-list refusal is earned. The layout makes the critical warning scannable.

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 an 11-parameter mutation tool with no output schema, the description covers the most consequential behavior (assignee replacement) thoroughly. Gaps remain: it does not describe success/return behavior, interaction between est_hours and per-assignee estimated_hours, or expected date string formats. These are secondary, but for a tool this complex the description is not fully complete.

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 low (36%), so the description must compensate. It adds real value: case-insensitivity for priority/status beyond the enum-style schema text, and detailed replace-vs-add semantics for assignees that go beyond the schema's one-line warning. It does not cover remaining undocumented params like archived, due_date, or is_milestone, but it focuses on the highest-risk parameter.

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?

"Update fields on a task" states a specific verb and resource, clearly distinguishing the tool from read/create/delete siblings in the tasks_* family. It is clear and unambiguous, though sibling differentiation is carried mostly by the name and title rather than explicit contrast in the description.

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 description provides clear operational context, including the critical prerequisite "read the current one from tasks_get first if you are only adding a person," which routes the agent to the correct read-before-write sequence. It does not explicitly state when-not-to-use this tool versus alternatives like tasks_create or tasks_add_dependency, but the guidance is sufficient for correct invocation.

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