list_jobs

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial behavior beyond that: content-addressed identity surviving renames and moves, persistence across sessions and machine restarts, that unreadable manifests are silently omitted, that an empty list is not proof of no sources, and that gc can explain a disappeared job. This is exactly the kind of non-obvious semantics annotations cannot convey.

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?

Front-loaded correctly: purpose and field list first, caveats second, usage rules third, examples last. The example list is long (eleven bullets) and a few overlap in intent ('match by filename/created' vs 'same filename -> newer created'), but each covers a distinct scenario, so the volume is defensible rather than padding.

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 parameterless list tool with an output schema, the description covers the remaining risk surface: staleness/identity semantics, silent omission of broken manifests, empty-list interpretation, and the recovery path via process_media/process_url. Nothing an agent needs to call or interpret this correctly is missing.

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?

Zero parameters, so the baseline is 4; there is nothing to document. The description's field-level detail (duration, created, wall_clock.start, speakers, origin) describes the return payload rather than inputs, which is redundant with the existing output schema but harmless.

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?

Opens with a specific verb+resource and scope: 'List processed recordings, newest first', then enumerates exactly what a returned record carries (job_id, filename, duration, created, wall-clock start, counts). It also separates itself from the write-path siblings by noting that process_media/process_url are what rebuild a job, so an agent can tell 'list' from 'process' without opening a schema.

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?

Contains an explicit 'When NOT to use' section (not a health check, don't poll before every call) plus an anti-example ('checking whether a NEW file is processed -> just call process_media'). Multiple worked scenarios map user utterances to the call and name when to ask a follow-up question instead.

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