Change a task

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

Beyond the annotations, the description discloses that null is used to clear fields, that the operation is guarded by the entry's ETag, and that it preserves unspecified fields. These are meaningful behavioral traits not present in the annotations or schema. The description does not contradict the annotations; readOnlyHint=false, destructiveHint=true, and idempotentHint=true are all consistent with a patch-style update.

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 short sentences, each carrying distinct information: partial-update semantics, null clearing, ETag guard, and the routing to complete_task. There is no filler or repetition. The structure is front-loaded with the core behavior and follows with edge-case semantics and the sibling alternative.

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?

Given the output schema exists and annotations cover safety, the description conveys everything essential for correct invocation: what changes, what stays, how to clear fields, concurrency protection, and when to choose a sibling. It does leave the ETag supply mechanism unspecified, but this is likely a header-level concern not required in the tool description. Overall the description is complete for a 10-parameter tool with a partial-update model.

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 80%, so the baseline is 3. The description adds a general 'Pass null to clear a field' rule, but this is already documented for the nullable fields (categories, description) in the schema. It does not illuminate the two undocumented parameters, priority and percent_complete, and could be slightly misleading since several fields do not accept null. No meaningful additional parameter semantics beyond the schema are provided.

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 opens with a specific verb and resource: 'Changes the fields named', which clearly identifies a partial-update operation on a task. It also distinguishes itself from the sibling complete_task by explicitly saying that marking a task done should use that tool instead. This makes the tool's purpose unambiguous and separable from siblings at a glance.

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 gives an explicit alternative and the condition that selects it: 'To mark a task done use complete_task, which records the completion time as well.' This directly answers the most likely ambiguity with sibling tools. The phrase 'leaves everything else as it was' also tells the agent this is a targeted patch, not a full replace or creation operation.

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