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

Annotations already declare readOnly=false, idempotent=true, destructive=false, openWorld=false. The description adds real context beyond them: it does not start the local laptop process, a queued batch is not a completed simulation, submissionOrigin/ciContext are immutable caller declarations rather than attestations, and the operation key should be retained. This is substantive async/idempotency semantics the annotations do not convey.

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 sentence and each following sentence addresses a distinct operational pitfall. There is mild redundancy between 'immutable caller declarations… retain them with the operation key' and 'Remote MCP does not infer the customer's CI environment', but the text is dense and waste-free overall.

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?

Given an extremely large nested recipe schema, 6 parameters, and no output schema, the description adequately covers operational semantics but leaves recipe construction entirely to the schema and never indicates what a successful call returns (e.g., a batch id for later polling via firedrill_batch). For a tool of this complexity, that is a meaningful gap.

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 only 17%, so the description must compensate, and it does for the hardest parameters: it clarifies that submissionOrigin and ciContext are immutable caller declarations (not target-source or workflow attestations), that the operation key is the retention handle, and that the recipe must already be validated. It still says nothing about the recipe's internal structure or projectId/environmentId format, but adds genuine meaning for the ambiguous fields.

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 pair (persist a validated recipe, queue its runs) and names the resource and scope (explicit project/environment). It is distinguishable from siblings like firedrill_validate_recipe (validation), firedrill_preview, and firedrill_batch (read a batch), 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?

Usage is implied rather than stated: 'a validated recipe' hints that validation precedes this call, and 'queued batch is not a completed simulation' tells the agent what to do next (continue with the customer-owned runner). But it never says when to choose this over firedrill_preview, firedrill_validate_recipe, or other batch tools.

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