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

With no annotations, the description carries the full burden, and it delivers: it discloses the bypass behavior, the precondition that 'the entity must already exist,' and the exact synthesized trigger context shape { entity_type, entity_id, payload }. It stops short of warning that firing a workflow may have real side effects such as emails or record mutations, which would be valuable for a mutation tool with zero annotation coverage.

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 sentences, each earning its place: action plus differentiator, use cases with an illustrative example, and preconditions plus context semantics. The essential scoping information is front-loaded ahead of the longer motivational example, with 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?

For a tool with no output schema, the description covers purpose, selection criteria, preconditions, and context formation — the bulk of what an agent needs to call it. The gaps are the undocumented return value (with no output schema, an agent cannot learn what a successful fire returns, e.g., a run ID to track via workflows_runs) and behavior with paused workflows.

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 100%, so the baseline is 3, but the description adds runtime meaning beyond the schema by mapping the parameters into the synthesized trigger context ({ entity_type, entity_id, payload }) and stating the entity-existence precondition on entityId. This tells an agent how the four parameters interrelate at execution time rather than just describing each field in isolation.

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 names a specific verb and resource — 'Manually fire a workflow on a specific entity' — and adds the distinguishing trait 'bypassing its trigger,' which separates it from normal trigger-driven execution and from siblings like workflows_pause, workflows_resume, and workflows_runs. The concrete example ('run my onboarding workflow on John Doe') further pins down the operation. No other sibling tool claims to execute a workflow.

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 gives explicit when-to-use scenarios: 'testing a workflow you just authored, or for one-off automations the user invokes by name.' It implies the negative case — when the workflow's own trigger would fire — by emphasizing 'bypassing its trigger,' but it never explicitly names an alternative tool or a when-not-to-use condition.

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