ispw_promote_assignment

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, so the description does not need to re-state the safety profile. It does add genuine context beyond annotations: promotion mutates the assignment AND all of its tasks, and the return value is an operation ID plus a status URL, implying an asynchronous operation the agent must poll. It does not say what happens on failure or whether a promotion can be reversed.

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?

Purpose is front-loaded in the first line, followed by lifecycle context, then Args/Returns/Examples. The structure is skimmable and every section serves a purpose. There is some redundancy in re-listing parameters already present in the schema, and 'Returns' largely duplicates what the output schema covers, but neither is wasteful enough to hurt.

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, non-idempotent lifecycle tool with an output schema, the description covers purpose, timing, all inputs, and the shape of the response. Minor gaps remain: no statement about error/failure behavior, permissions, or whether the call is blocking versus poll-based, which matter given the operation-ID/status-URL return.

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?

Although schema description coverage is 0% by the metric, the Args block restates and enriches every parameter: srid, assignment_id, the target level, change_type with its S/I/E meanings, execution_status, and response_format. The one soft spot is 'execution_status', which is repeated verbatim without any explanation of valid values or effect, and target levels are only implied via the body examples rather than listed as accepted values.

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 first sentence gives a specific verb + resource ('Promote an ISPW assignment'), and the second pins down the exact effect: moving the assignment and its tasks from DEV to INT, INT to ACC, or ACC to PRD. This clearly distinguishes it from siblings like ispw_generate_assignment, ispw_deploy, and ispw_create_assignment, which do different lifecycle steps.

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?

'Typically done after successful generation and testing' gives a real precondition for calling this tool, and the lifecycle examples imply when in the workflow promotion applies. However, it never explicitly names alternatives (e.g., 'use ispw_deploy for the final move to production') or states when not to promote, so it falls short of full alternative routing.

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