update_workflow

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

No annotations are provided, so the description carries the burden. It discloses that completed, failed, and cancelled are terminal states—useful behavior not present in the schema's enum alone. However, it does not mention permissions, reversibility, downstream effects, or what happens after a terminal state, which are important for a mutation tool with no 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?

Two sentences with no fluff. The action is front-loaded, the usage guidance follows, and the terminal-state note is a compact addition that earns its place. Everything present contributes to selection and invocation.

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 and no annotations, the description covers the core action, the triggers, and a critical behavioral fact (terminal states). It does not promise a return value or detail errors, but for an update-offloaded to schema for parameter detail, the description gives the agent enough to use the tool correctly.

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 only 25%. The description adds meaning to 'status' by explaining that completed, failed, and cancelled are terminal, and it describes 'summary' as optional. It does not elaborate on workflow_id or binding_token beyond the schema, leaving most of the parameter load on the schema. This is adequate but does not fully compensate for the low coverage.

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 starts with 'Update a WORKFLOW status and optional summary', which states a specific verb (update), a resource (WORKFLOW) and the fields affected (status and summary). It clearly differentiates from sibling tools like start_workflow (creation) and update_task (task resource), and the examples 'all workers finish' and 'final aggregation is complete' reinforce the workflow-scoped purpose.

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 explicit trigger conditions: 'Use when all workers finish, a workflow blocks, or final aggregation is complete.' This is clear guidance on when to invoke the tool, but it does not provide explicit exclusions or alternative tool names, such as 'don't use update_task for tasks', so it misses the top rung.

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