swsd_update_incident_state

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

Annotations already carry the mutation profile (readOnlyHint=false, destructiveHint=true, idempotentHint=false), so the bar is lower. The description adds genuine value beyond them: 'WRITE — does not retry on transient failure' discloses a retry policy absent from the annotations, and the tenant-specific state caveat warns about environment-dependent behavior. No contradiction — the description's 'WRITE' and 'Transition' align with readOnlyHint=false and destructiveHint=true.

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 purposeful sentences, front-loaded with the core action and ending with the most safety-critical warning (no retry). The state-value list is somewhat redundant with the schema's state description, and the paragraph could be tightened with structure, but every sentence otherwise earns its place and nothing is fluff.

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 two-parameter mutation with full schema coverage and a complete annotation set, the description covers the action, the sibling rationale, the prerequisite call, tenant-specific state caveats, and no-retry behavior. The only material gap: there is no output schema and the description never hints at what a success or error response looks like — a minor omission for a write operation.

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%: the id parameter already explains internal-id vs human-facing-number auto-detection, and the state parameter already documents valid tenant values including the common list. The description's state examples and 'tenant-specific' warning largely restate the schema's own state text, so it adds minimal semantic value beyond the baseline 3 that high schema coverage earns.

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+resource+object ('Transition an SWSD incident to a new state') and immediately distinguishes itself from the raw update sibling by calling itself a 'safer wrapper around swsd_update_incident.' Listing concrete example states ('Assigned', 'Resolved', 'Closed') lets an agent know exactly the operation's scope and how it differs from the 35 sibling tools.

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 sequencing prerequisite — 'Call swsd_get_incident first to see the current state' — and steers the agent toward this tool over the broader update by framing it as a wrapper that 'narrows the agent decision surface.' It stops short of a 5 because it never names when-not conditions for overlapping siblings like swsd_assign_incident or swsd_update_task_state.

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