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

Annotations already flag destructiveHint=true, openWorldHint=true, and idempotentHint=false, and the description goes further: it discloses that start_anyway ends stopped runs with no checked result and records who chose it, warns that an earlier run may already have applied changes, and describes the failure return (current state plus reason). That is meaningful consequence disclosure beyond the flags.

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?

The precondition and the return behavior are front-loaded, but the middle is a dense, run-on clause ('start_anyway ends the case's stopped runs that have no checked result, recording this person, so the approved plan starts') that takes effort to parse. Every sentence carries information, but the phrasing is not tight.

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 7-parameter destructive retry with no output schema, the description covers the trigger condition, the dangerous escape hatch, the residual-risk warning, and the failure return shape. It omits idempotency semantics and any guidance on the required case/company/environment scoping, which keeps it short of complete.

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 71% and the schema already documents start_anyway, authorization, idempotency_key, company, and environment. The description adds behavioral meaning to start_anyway (it terminates stopped runs and records the person) and to authorization (attribution is recorded), but says nothing about idempotency_key reuse or the case parameter, so it only partially exceeds 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?

It names a specific action (retry a saved plan approval) and the precise precondition (the approval is waiting to start), plus where to obtain the id. That distinguishes it from summer_actions_approve and summer_actions_prepare, though the phrase 'try ... again' is vaguer than an explicit verb like 'resume'.

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 entry condition is explicit and points to investigations.list planApprovals for the id, and it states that a still-running run keeps blocking, which tells the agent when retrying will fail. It doesn't explicitly contrast with the sibling approve/prepare tools, so there's a small gap.

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