replay_build

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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=true, but the description adds the material consequence the flags cannot convey: the build is real and can deploy. The retry caution on an uncertain POST translates the non-idempotent flag into actionable agent behavior, which is exactly the value-add expected above the annotation baseline.

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 short sentences, front-loaded with the action and its scope, followed by the side-effect warning and then the two operational rules. Nothing is redundant and the most dangerous fact (real build, can deploy) is placed early.

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 destructive, non-idempotent mutation with no output schema, the definition covers side effects, prerequisite tooling, and retry safety, which is the bulk of what an agent needs before calling. The remaining gap is identification of the fullname and build-number parameters, whose semantics are left entirely to the agent's inference.

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 0%, so the description carries the full burden, and it only partially delivers: it establishes that mainScript is a *replacement* (meaningful beyond the schema) and that loadedScripts is optional, but says nothing about fullname or the build number parameter, nor about the nested script map's key/value meaning. Partial compensation for a four-parameter tool.

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 names a specific verb and resource ('Run an existing Pipeline build again') and clarifies that the run substitutes a new mainScript rather than creating a fresh build. That distinguishes it reasonably from build_item, though it never names build_item explicitly, so sibling differentiation is implied rather than stated.

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 a hard prerequisite ('Read get_replay_scripts first') and an operational rule ('Never automatically retry after a submitted/uncertain POST'), which are concrete when-to-use/when-not-to-act instructions. It stops short of stating when an agent should pick this over a fresh build via build_item, leaving one routing decision to inference.

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