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

Annotations already declare destructive=true, idempotent=true, readOnly=false and openWorld=false. The description adds valuable behavior beyond that: it spends one credit from the VecSnap account, only once per image, and returns the file link. It still doesn't explain insufficient-credit handling or link expiry, but the cost model is the key undisclosed behavior and it's covered.

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 with no filler: first restricts the caller, second gives trigger, cost and result. Front-loaded and appropriately sized for a one-parameter mutation.

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 destructive, idempotent, one-parameter tool with annotations and no output schema, the description covers caller restriction, trigger, credit cost and return value. It leaves minor gaps around failure modes and link lifetime, but nothing essential for correct invocation.

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 100% and the schema itself explains conversion_id as the ID returned by vectorize_image. The description does not mention the parameter or add any format/source detail beyond the schema. Baseline 3.

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 the trigger (person pressed Download), the cost (one credit, once per image), and the result (answers the file's link). The name is unlock_file, and the description makes clear it unlocks a file by charging a credit. It distinguishes from siblings by restricting to the VecSnap card, though it doesn't explicitly name an alternative.

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?

Provides a strong context: only the VecSnap card calls this, after the person pressed Download. This implicitly excludes other callers, but no alternative tool is named and there is no explicit 'do not use for X' guidance. An agent knows the intended path but not what to do if invoked from elsewhere.

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