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

Annotations already declare readOnly/idempotent/non-destructive, so the 'Changes nothing' clause is redundant, but the description adds genuinely new behavior: this is an asynchronous job that must be re-polled until done is true, and the agent should narrate progress while the board shows it. That polling/settling semantics is not derivable from the annotations and is the key thing an agent needs.

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 with the usage trigger, then return shape, then polling loop, then follow-up - a sensible order. Somewhat run-on with stacked parentheticals, but every clause carries information; nothing is 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?

No output schema exists, and the description does the necessary work by enumerating what comes back (status, credits, results, failures, done). With annotations covering safety, the main gap is the undocumented workflow_run_ids parameter and the exactly-one constraint, which leaves it slightly short of fully self-contained.

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 coverage is only 33% - only board_id carries a schema description, and the object-level 'exactly one' note is the only guidance for brief_id vs workflow_run_ids. The description references brief_id in passing but says nothing about workflow_run_ids (up to 50 UUIDs) or the mutually exclusive selection, so it fails to compensate for the coverage gap.

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 clearly what the tool returns: each look's run for a brief_id with status, credits, results (generation_result_id, kind, url) and per-step errors. The verb is implicit ('follow' / 'how a shoot is going') rather than a crisp verb+resource, but an agent can determine what the call produces. It distinguishes itself from confirm_brief (upstream) and get_generation_results (downstream), though not from the sibling get_generation_status.

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?

Explicit trigger conditions: 'after confirm_brief or when the user asks how a shoot is going', plus a polling instruction ('Read it again until done is true') and a downstream routing hint ('show the results with get_generation_results'). No exclusion statement, and it never contrasts with get_generation_status, so a sibling ambiguity remains.

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