execute_workflow

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

Annotations only say readOnlyHint=false and destructiveHint=true; the description adds two genuinely new traits: execution halts at the first failed step (implying partial completion with no rollback) and an approval gate tied to the user's explicit yes. It stops short of saying what happens to already-executed steps on failure, which is the key open question for a destructive tool.

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 short sentences, front-loaded with the action and then the two critical constraints; nothing is padding. The phrase "from the user's yes" is awkwardly worded for what should be a precise provenance requirement on approved_hash.

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-looking executor with no output schema and zero schema documentation, the description covers approval and failure behavior but omits what plan_id refers to, whether completed steps persist after a mid-run failure, and what is returned. Adequate but leaves real gaps for a high-risk mutation.

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 both parameters. It does explain approved_hash as coming from an explicit user confirmation, which is meaningful, but plan_id is only obliquely covered by "a plan" with no format or origin specified.

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?

"Run a plan the user approved" gives a specific verb (run) and resource (a previously approved plan), which separates it from propose_workflow and discover_capabilities. However, it never distinguishes itself from the sibling run_saved_workflow, so an agent cannot tell which executor to pick from the description alone.

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 approval precondition ("the user approved", "approved_hash from the user's yes") implies when this tool is callable, but it offers no explicit when-not guidance and no comparison to run_saved_workflow or propose_workflow. Usage must be inferred from the sibling list.

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