swsd_update_task

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

Annotations already flag this as a non-readonly, destructive, non-idempotent, open-world write. The description adds real context beyond that: it honors SWSD_WRITE_MODE (a write-gating switch) and deliberately does not retry on transient failure, which changes how an agent should handle errors. It stops short of saying what 'destructive' means here (e.g. whether clearing a field or overwriting assignee is lossy).

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?

Three short sentences, front-loaded with the action and the required identifiers, then the write caveats. The parenthetical re-listing of parameters is slightly redundant given full schema coverage, but nothing is padded or ambiguous.

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 six-parameter mutation with no output schema and full schema documentation, the description covers the essentials an agent needs: required ids, partial-update behavior, write-mode gating, and the no-retry policy. It leaves the return value and the concrete meaning of SWSD_WRITE_MODE values unstated.

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 100% and the schema already explains incident_id auto-detection, task_id provenance, and ISO 8601 with timezone. The description's material addition is the patch semantics ("only provided fields are sent"), which clarifies that omitted fields are left untouched rather than nulled; the rest restates the schema.

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?

States a specific verb and resource: updating a SWSD incident sub-task, and enumerates the mutable fields (name, assignee_email, due_at, is_complete). It does not explicitly differentiate itself from the sibling swsd_update_task_state, which overlaps on the completion field, so the agent must infer the boundary.

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 provided fields are sent" implies a partial-update contract and the field list suggests when to reach for it, but there is no explicit when-to-use/when-not guidance and no named alternative such as swsd_update_task_state or swsd_create_incident_task.

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