Watch Job

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

The description adds extensive behavioral context beyond the annotations (which only indicate not read-only). It details continuous polling, deep failure analysis, auto-correction, and resubmission up to max_retries times. No contradiction with 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?

The description is concise (two short paragraphs) with a front-loaded main purpose. Every sentence adds value, and the structure logically flows from overview to failure handling to additional use case.

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?

Given the tool's moderate complexity (3 parameters, output schema present), the description is fully adequate. It explains the overall workflow, failure handling, and additional use cases without needing to detail return values since an output schema exists.

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?

The input schema has 100% description coverage, so the baseline is 3. The description adds value by linking parameters to behavior: 'polls continuously' for poll_interval, 'auto-correct-and-resubmit cycles' for max_retries. This enhances understanding beyond the schema.

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 uses a specific verb ('Watch') and resource ('Beaker job'), clearly stating the tool's role: monitoring until completion with failure analysis and auto-retry. It implicitly distinguishes from siblings like get_job_status (which just polls without analysis) and submit_job (which submits without watching).

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 explicitly states when to use the tool ('Watch a Beaker job until completion') and mentions additional use cases ('works on already-finished jobs for post-mortem analysis'). It does not explicitly state when not to use it (e.g., for one-time status checks), but the context is clear enough.

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