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

Annotations already declare readOnly/openWorld/non-destructive, and the description adds real behavior: wait_seconds acts as a long poll that blocks until the next step, and the tool has a state machine (awaiting_checkpoint) with a required hand-off to approve_checkpoint. It omits return shape outside the delivered/checkpoint cases, timeout behavior, and what happens when wait_seconds elapses with no step change, so it is useful but not thorough.

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 content is dense but packed into run-on clauses, and there is no front-loaded one-sentence summary of what the call returns. Little is pure filler, but the structure is hard to scan and mixes return-field inventory with multi-step workflow instructions.

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 and 0% parameter coverage, the description has to describe both inputs and returns; it covers the delivered and checkpoint payloads reasonably well but leaves n/series_id undefined, defines neither 'quote' nor 'plan balance', and says nothing about the ordinary in-progress response envelope.

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 carry the parameter burden, yet only wait_seconds is explained (0-40, use 40 while filming). The required n and series_id are never defined; 'episode X of Y' hints that n is the episode number but nothing states the indexing convention or whether series_id is a slug or ID.

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 names the concrete payload (job progress, phase completion, per-scene line checks, quote, plan balance, public MP4 URL) which makes clear this is an episode status reader. It never states the core verb in one clause, and it is not explicitly differentiated from near-siblings like get_latest_episodes or get_run_status, but the returned-field inventory is specific enough to distinguish it.

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?

It gives strong conditional routing: when status is awaiting_checkpoint, show it, post say, STOP, and call approve_checkpoint only after the user's yes. It also explains when to use wait_seconds=40 (while filming). It does not say when to prefer this over other episode-reading siblings, but the workflow guidance is concrete.

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