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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds genuinely non-redundant behavior: partial-update semantics, that the updated record is returned, and the underlying PUT /tasks endpoint. It could still warn that overwriting descriptionHTML replaces the existing body, which is what makes a partial update destructive.

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 short sentences after a front-loaded "WRITE:" tag; the partial-update caveat and return value each carry weight and nothing is padded.

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 5-parameter mutation with no output schema, it covers the mutation contract, partial semantics, and return shape adequately. The missing pieces are the required id and any overwrite warning for descriptionHTML.

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 60%, and the description largely restates what the schema already declares (title, status enum values, due date, description HTML). It does not mention the required `id` parameter at all, so it fails to compensate for the coverage gap on the one parameter without a schema explanation.

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?

"WRITE: change a task's title, status, due date or description" gives a specific mutation verb plus resource and enumerates the mutable fields, which is enough to separate it from plutio_create_task. It stops short of naming any sibling or stating the precondition (task must already exist), so it isn't fully differentiated.

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?

"Only the fields you pass change" implies partial-update usage and steers the agent away from full-object replacement, which is real guidance. However there is no explicit when-to-use vs. plutio_create_task, no note that the task id must come from a list call, and no exclusion guidance.

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