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

With no annotations, the description carries the full behavioral burden and does well: it discloses the detection surfaces it inspects, that a verdict is returned with method and location, and that recovered text is returned separately and marked untrusted. It omits resource concerns like size limits or latency, which the schema hints at only indirectly.

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?

Three tight sentences with zero filler: purpose first, invocation constraint second, result and safety handling last. Every sentence carries distinct information and the most important clause is front-loaded.

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?

There is no output schema, so the description must cover return behavior — and it does, stating what the response reports (whether found, how, where) and that recovered text arrives separately. For a 3-parameter tool with 100% schema coverage, nothing an agent needs to call it correctly is missing.

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%, so the baseline is 3, but the description adds real meaning the schema lacks: the mutual exclusivity of image_url and image_base64, and the https requirement. The mime_type behavior ('the file's bytes decide') is already in the 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?

States a specific verb (find/check) and resource (image) plus the exact threat model it targets: instructions hidden for AI assistants in metadata, faint/tiny text, or text revealed when shrunk. That specificity distinguishes it from siblings like scan_text, scan_url, and check_ai_image without needing their schemas.

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 invocation rule — pass image_url (https) or image_base64, not both — which is clear usage context. It does not, however, name an alternative tool or state when this should be preferred over check_ai_image or scan_text for the same content.

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