gc_workflow_watch

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 this is an SSE/streaming watch mode, that it terminates on settle/timeout/abort, and mentions the client can abort. However, it doesn't describe auth requirements, what happens if the workflow is already settled when watch begins, or how stream events are batched or ordered beyond the 'since' seq parameter. The core behavioral traits are disclosed but some edge behaviors are underspecified.

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 tight sentences. The first states what the tool does (live SSE watch, event collection, terminal conditions). The second provides the alternative. Zero wasted words, fully front-loaded.

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 streaming watch tool with no output schema, the description conveys the essential lifecycle: events until settle/timeout/abort, with a simpler polling alternative. The return value is implicit (status events) and the terminal conditions are spelled out. Minor gaps: no mention of what 'settles' means precisely or whether the stream is resumable across aborts, but for a watch tool the core contract is adequately defined.

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 all 5 parameters are already documented in the schema. The description adds context by explaining the event-collection lifecycle (until settle/timeout/abort) that the parameters operate within, and the sibling alternative clarifies that 'since' and 'timeout' relate to a streaming semantics not present in the polling mode. It adds modest value over the schema's per-parameter descriptions.

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 clearly states this is a live SSE watch of workflow execution that collects status events until settlement, timeout, or client abort. The verb 'watch' plus resource 'workflow execution' is specific and it distinguishes itself from the sibling gc_workflow tool by explicitly naming action=wait as the polling alternative.

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?

Explicitly directs when to use this tool ('collects status events until the execution settles, times out, or the client aborts') and provides a direct alternative: 'Use gc_workflow action=wait for a simpler polling alternative.' This names the sibling tool and its specific action, giving clear exclusion guidance.

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