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

Annotations already flag destructiveHint=true and openWorldHint=true, so the description's job is to say what is destructive — and it does: passing explicit null wipes nullable fields (dueDate, parent, taskType). It adds lenient name resolution behavior and the required API-key scope (`tasks:write`), which 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?

Five tight sentences, front-loaded with the partial-update contract, zero filler, and the sibling routing placed near the end where it belongs. The one soft spot is "Names resolve leniently against the current effective set," which is compact but under-defined.

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 20-parameter destructive mutation with no output schema, the description covers the essentials an agent needs to avoid mistakes: partial semantics, null-clearing, sibling routing, and auth scope, with account/workspace handled in the schema. What is missing is guidance on the nested customFields object and the ordering/date formats for the many nullable string fields.

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?

With 20 parameters and only 35% schema description coverage, the description must carry weight, and it does explain the cross-cutting null/omit distinction plus taskType's special case. But roughly a dozen parameters (status, priority, level, nextTo, assignees, customFields, estimatedTime, isPrivate, tags, description, startDate, list) get no semantic guidance in either place, so the compensation is partial.

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?

"Partial-update a task by ref" gives a specific verb, resource, and update model in one clause, and the description explicitly contrasts itself with pm_bulk_change_task_type. An agent can distinguish this from pm_create_task, pm_get_task, and the bulk-type sibling without opening a 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?

It states the routing rule outright: use this with `taskType` for a single-task type change, use `pm_bulk_change_task_type` when changing many tasks at once. It also states the partial-update contract (only fields present change) and the allowlist condition for clearing values, which tells the agent how to structure the call rather than leaving it to inference.

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