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

Annotations only give generic hints (readOnlyHint=false, idempotentHint=false, openWorldHint=false), while the description adds substantial non-generic context: no server model call, no tool use, no sending; the returned payload is frozen instructions; request_id may only be reused with identical inputs; and the results are caller attestations rather than verified provider usage. The permission requirement (workflows:run) is also disclosed. None of this is derivable from the annotations.

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?

Five short sentences, each carrying a distinct fact (what it starts, what it returns, what it does not do, the request_id rule, the trust level, the permission). Front-loaded with the core purpose and no filler.

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?

With no output schema, the description usefully tells the agent what comes back (frozen instructions to execute) and what the eventual results mean (attestations, not verified usage), plus the auth requirement. It is slightly thin on the query/workflow parameters, but for a 3-parameter tool the description covers the operational essentials.

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 is the only source of parameter meaning. It only explains request_id semantics (idempotency-key-like: reuse only with identical inputs), leaving 'workflow' and 'query' entirely unaddressed despite their being required. That is genuine added value but far short of compensating for the coverage gap.

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 ('Start a caller-executed sales evidence draft') and immediately qualifies the outcome ('Returns frozen instructions for your agent to execute'), so the agent knows this is a producer of instructions, not an executor. It does not explicitly differentiate itself from the closely-named siblings get_external_workflow, review_external_workflow or submit_external_workflow_result, which is the only thing keeping it from a 5.

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 description implies the intended flow (server hands back frozen instructions that the caller's agent then executes, and results come back as attestations), which points toward the submit_external_workflow_result sibling. But it never says when to choose this over run_workflow or review_external_workflow, nor when-not to call it, so usage is inferred rather than stated.

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