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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds real value beyond that: the returned fields (including cue count and SRT readiness) and the polling pattern. It doesn't describe terminal/failure states or error behavior, so not a 5.

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 sentences, zero filler, with the resource and returned fields front-loaded ahead of the usage hint. Nothing could be removed without losing information.

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?

With no output schema, the description usefully enumerates what comes back, and the single-parameter schema needs little more. A gap remains around status values and what to do when the job fails or the SRT is not yet ready, which matters for a polling tool.

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 100% and the single parameter is fully documented in the schema as 'the job id returned by lunara_upload_video'. The description adds no new syntax, format, or sourcing detail beyond that, so the baseline 3 applies.

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?

States a specific verb and resource ('Return the state of a subtitle job') and enumerates the exact payload fields (status, progress, SRT readiness, cue count). This enumeration is what separates it from neighbors like lunara_get_srt and lunara_list_cues, which return content rather than job state.

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?

'Poll this after lunara_upload_video' gives a concrete trigger, sequencing, and the fact that repeated calls are expected. It stops short of naming when-not to use it or pointing at the sibling to call once the SRT is ready (lunara_get_srt), so no explicit exclusions.

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