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

Annotations declare idempotentHint=true, destructiveHint=false and readOnlyHint=false, so the mutation profile is largely handled structurally. The description adds real value beyond that by disclosing resumption semantics: it continues from the last valid step rather than re-running from scratch and is non-destructive. It omits what happens if the project is not in FAILED status or whether the retry is long-running.

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?

A single sentence with no filler, front-loading the action and the state constraint. Every clause earns its place.

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 one-parameter action whose safety profile is covered by annotations and whose return values are covered by an output schema, the description is essentially sufficient. Minor gaps: failure behavior on non-FAILED projects and whether the operation is asynchronous.

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?

Only one parameter and schema description coverage is 100%; the schema already states 'Project in FAILED status.' The description reiterates the same constraint, adding no format, ID-source, or lookup guidance beyond it. Baseline 3 applies when the schema carries the parameters.

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 (resumes) plus the resource (project) and its applicable state (FAILED status). The clause 'from the last valid step, without starting over' makes it distinguishable from a fresh-start tool like start_clipping or generate_clips, though no sibling is named explicitly.

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?

The precondition is clear: the project must be in FAILED status, which is the when-to-use condition. It does not state what to do instead when the project is not FAILED, so the alternatives side is left to inference.

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