job_watch

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering safety. The description adds behavioral context by calling it a 'long-poll endpoint' and specifying it waits for 'one job version change' rather than terminal completion. This is useful beyond the annotations, though it doesn't mention timeout or return format.

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?

The description is two sentences with no filler. The first sentence states the core action, and the second provides essential usage differentiation. Every word earns its place.

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?

The description excels at tool selection and sibling differentiation, and annotations cover safety. However, with four parameters and no output schema, the lack of parameter explanation and return behavior leaves the agent to infer too much for correct invocation. It is adequate but has clear gaps.

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 compensate, but it does not explicitly explain any parameters. It only hints at the meaning of afterVersion through 'version change.' The roles of tailLines and timeoutMs are left entirely to the schema, which provides no 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 the tool's function: 'Wait for one job version change.' It uses a specific verb and resource, and explicitly distinguishes itself from sibling job_wait by noting this is for the RunBeacon dashboard while models should use job_wait for terminal completion.

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 usage guidance: it is intended for the RunBeacon dashboard, and models should use job_wait for terminal completion. This directly tells when to use this tool versus an alternative, fulfilling the 'when/when-not/alternatives' criterion.

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