Update a task

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

The description discloses mutation semantics ('Mutating; last write wins'), error behavior ('Missing ids return task_not_found'), and authorization context ('Auth: tool policy gate'). These add real behavioral context beyond the annotations, which already mark this as non-read-only and non-idempotent.

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?

Four sentences, each carrying distinct value: what it patches, when to use it, what not to use it for, and key behavioral caveats. No filler, no repeated schema text, and the most important info is front-loaded.

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 mutating update tool, the description covers usage timing, exclusions, mutation semantics, error cases, and auth. The output schema exists, so return-value explanation is unnecessary. Sibling-tool disambiguation is already handled, making this complete for an agent to select and invoke 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%, so the schema already documents all parameters. The description names the relevant fields but adds no new semantic detail beyond what the schema provides; 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?

The description uses a specific verb ('Patch') with a clear resource ('an existing task') and enumerates the exact fields affected: status, progress, message, result, error. It also explicitly differentiates from sibling tools by saying what it is not for (cancel via tasks_cancel, create via tasks_create).

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 gives an explicit usage context ('Use while a worker is running') and names the alternatives to avoid ('Do not use to cancel — that is tasks_cancel — or to create a new handle (tasks_create)'). This is strong, unambiguous routing guidance.

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