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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so safety is covered. The description adds genuinely new behavioral context beyond that: the response shape is polymorphic, returning a condensed storyboard descriptor (id, name, scene count, app_url) for certain runs instead of full run data. That is a useful disclosure an agent could not infer from the annotations.

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. The core purpose and return contents are front-loaded, and the storyboard caveat follows immediately after, which is the right order for an agent scanning the definition.

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?

An output schema exists, so return values need not be enumerated, and annotations carry the safety profile; combined with the storyboard caveat, the definition is largely sufficient. It stops short of the full picture only in omitting how this relates to run-lifecycle siblings (resume, retry, cancel, decide_workflow_items), which affects 'what do I do next' rather than 'how do I call this'.

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?

There is one parameter, run_id, with 0% schema description coverage, so by the rubric the description must compensate — and it adds nothing about it. However, the parameter is self-evidently a run identifier and the schema supplies its uuid format, so the practical ambiguity is low; a 3 reflects adequate-but-uncompensated semantics rather than a real 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 a specific verb and resource ('Read a workflow run') and enumerates what is included: recorded steps, generations, and current checkpoint. It further distinguishes itself from get_storyboard by explaining that runs which build a film report a compact storyboard summary instead, so an agent can tell the two tools apart 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?

Gives a concrete routing rule: when a run is film-building, read the board itself with get_storyboard rather than this tool. That is explicit when-to-use-a-sibling guidance, but it says nothing about the other obvious siblings (list_workflow_runs for discovery, resume/retry/cancel for acting on a run), so the coverage is partial rather than complete.

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