Job List

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

Annotations declare readOnlyHint=true, and the description consistently describes a pure listing operation. It goes well beyond the annotations by disclosing submit ordering, session scoping, the 'drained once per request' behavior, and the meaning of pending versus drains for diagnosing a stalled optimization.

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 front-loaded with the core purpose and then provides a compact return-shape specification. The second sentence earns its place by explaining the non-obvious main_thread_queue diagnostics rather than padding with redundant prose.

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?

There is no output schema, so the description must explain return values, and it does: the count, jobs array fields, ordering, and the main_thread_queue diagnostic. For a parameterless read-only tool, this is enough for an agent to know what it will get and how to interpret it.

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 tool has zero parameters, so there are no param semantics for the description to clarify; baseline 4 applies. The description instead usefully documents what the returned fields mean, which is the relevant information for a no-argument tool.

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 opens with a specific verb and resource: 'List every async job this worker session,' which clearly establishes scope. It also states the return shape, making the tool's function unambiguous. The session-scoped, all-jobs framing distinguishes it from siblings like job_result or job_status, which focus on individual jobs.

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 provides a clear use context: it is 'the diagnostic for a shape optimization that looks stuck,' including how to interpret main_thread_queue counters. It does not explicitly name alternatives such as job_result or job_status or state when not to use this tool, so it falls short of a 5.

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