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

Annotations declare a non-read-only, idempotent, non-destructive write; the description adds genuinely new context beyond that: it consumes 'bounded service capacity, not a payment' and that 'no sample data/actor is inferred.' These clarify cost/consumption semantics not present in annotations. It does not elaborate on the operationKey/idempotency relationship beyond what the schema already says.

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 dense sentences with no filler; the core allocation behavior is front-loaded, followed by capacity semantics and the recipe alternative. The phrasing is jargon-heavy but every sentence adds information.

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 6-required-param mutation with no output schema and low schema coverage, the description covers purpose, capacity, and the recipe alternative but omits the meaning of ttlSeconds and the identity params, and says nothing about the return (e.g., instance id/handle) an agent needs to proceed.

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 only 13%, so the description carries most of the burden, and it compensates partially by clarifying that seed and actor operations must be explicit and that build/dataset are exact and immutable. However, ttlSeconds, projectId, and environmentId get no explanation in either schema or description, leaving real gaps.

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: 'Allocate one manual service instance from an exact immutable build and optional dataset.' This clearly distinguishes it from sibling tools like firedrill_service_acquire or firedrill_service_invoke, though it never names those alternatives explicitly.

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?

Provides an explicit when-not and alternative: 'For independent recipe cases bind services in the recipe instead; the runner allocates isolated run-owned instances.' That routes the agent away from this tool for recipe-driven cases, but no positive trigger conditions or prerequisites (permissions, project/environment context) are given.

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