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

Adds substantial context beyond the annotations: caller provenance is retained while model_label is self-reported (a trust-boundary disclosure), no server model call or outbound action occurs, and retry semantics are given ('identical retries are safe; conflicting/stale results fail'). The annotations already cover the safety profile, so this extra detail is the value-add. The retry-safety wording sits uneasily against idempotentHint=false, but 'safe' can reasonably mean a duplicate is rejected rather than re-applied, so it is not a hard contradiction.

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 dense, front-loaded sentences with no filler: binding keys first, then provenance/trust, retry behavior, side-effect scope, and the required permission. Every clause carries information an agent needs before calling.

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 5-required-param mutation with no output schema and no parameter descriptions, the description covers the important behavioral unknowns (no outbound side effects, permission required, duplicate/stale handling). It falls short only on what a successful submit does downstream (e.g., whether the workflow advances) and on session_id semantics.

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 0%, so the description must carry all parameter meaning. It clarifies output, input_sha (must equal the exact next_step value), step_index, and that model_label is self-reported, which is genuinely useful. However session_id is never explained, and format/range constraints (64-hex sha, UUID, step_index 0-19) are left entirely to 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?

States a specific verb ('submit') and resource ('your output' for an external workflow step) with the exact keys that bind it (input_sha, step_index), so an agent can tell it is the result-reporting counterpart to start_external_workflow/get_external_workflow. It never names those siblings explicitly, so differentiation relies on inference.

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?

Implies the trigger condition ('for the exact next_step input_sha and step_index') and states the prerequisite ('Requires workflows:run'), which effectively tells the agent when it is callable. It does not say what to do instead when the sha is stale or the step is already complete, and names no alternative tool.

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