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

Beyond the annotations (destructiveHint=true, idempotentHint=true, readOnlyHint=false), the description discloses exactly what is mutated (job and credit records), the narrow condition under which the destructive action triggers (queued/running job older than ten minutes), and that the refund happens only once. This is precisely the extra context annotations cannot carry.

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?

Four short sentences, front-loaded with the primary action, followed by the conditional mutation, the non-behavior, and the prerequisite. No filler or repetition; every sentence adds a distinct fact.

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 explained. Given the tool's mutation semantics, the description covers what is required to call it safely and correctly: input source, mutation scope, the conditional destructive path, and the guarantee that no generation is started.

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 0% with one required parameter, so the description must compensate. It does by specifying the project_id's provenance ('returned by prepare_media_project'), which is meaningful information absent from the bare 'type: string' schema.

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 states a concrete verb+resource: showing a saved Abracadabrax image or video project together with its existing job, plus the side effect of failing a stale job and refunding credits. It is clear, but it does not distinguish itself from sibling tools like get_media_job or update_media_project, which could plausibly cover similar ground.

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 supplies a real precondition (project_id must come from prepare_media_project) and an exclusion (it never starts a generation, implicitly routing generation to generate_media). It stops short of explicitly naming get_media_job or update_media_project as alternatives, so the selection logic is not fully closed.

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