detect_media

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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false, openWorldHint=true), and the description adds meaningful context beyond them: it consumes API credits, has sync/async behavior with async default, returns two different result shapes, and names the required auth scope. It does not say whether the job receipt carries an id or how long jobs live.

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?

Five short sentences, front-loaded with what the tool does, followed by cost, mode, return shape, and scope. Every sentence carries information an agent needs; nothing is redundant with the title or restates the name.

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?

With no output schema, the description correctly describes the two possible return shapes (detection JSON vs job receipt), which is the key missing structured info. It still omits how to proceed after an async receipt is returned, which matters for a tool whose default is async.

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 description coverage is only 20% (only idempotency_key is documented), so the description must compensate. It explains mode semantics ('sync and async (default)') and maps media values to 'image, PDF or video', but leaves input_path format and webhook_id unaddressed beyond their schema types.

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 ('Detect a watermark in an image, PDF or video'), which is clear and distinguishable from the sibling watermark_media (which presumably applies/embeds a watermark). It does not explicitly name that sibling, but the detect-vs-apply distinction is inferable from the verb.

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 notes sync and async modes with async as the default and that the response is either detection JSON or a job receipt, which implies when a follow-up (get_job) is needed. However, it never states when an agent should choose sync over async, nor references the get_job/get_job_result siblings that consume the receipt.

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