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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered structurally. The description adds genuinely useful non-schema behavior: the picker UI is interactive and thumbnailed, template/character works are filtered out, and hosts lacking a picker degrade to returning recent works with a text fallback. It stops short of noting that the call blocks on user interaction or that results are non-deterministic (non-idempotent), which would round out the behavioral picture.

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 the core action and return, then trigger, then exclusions, then fallback, then the sibling redirect. Every sentence carries distinct information and none repeats the schema or annotations.

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 shape need not be spelled out, and the description still states it returns the chosen URLs. Trigger conditions, exclusions, and the no-picker fallback are all present. The only missing piece is behavior during the interactive wait (blocking, timeout, cancellation) for a tool whose entire purpose is user interaction.

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 100%, with each of the three parameters documented, including the max range (1-6, default 1), the media enum, and the purpose field being prompt-wording only. The description adds no parameter-level detail beyond that, so the baseline 3 applies.

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 (choose media from a picker), the resource (recent finished images/videos), the intended downstream use (reference, first frame, edit source) and the return (chosen media URLs). It also explicitly carves out what it does NOT cover (template/character works) and names a different sibling (create_upload) for the adjacent case.

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 trigger ('when the user refers to an earlier work without naming one'), an explicit exclusion ('Works made with templates or characters are not listed'), a host fallback ('On hosts without pickers it returns the recent works: ask the user in text'), and an alternative ('A new file needs create_upload instead'). This is as close to when/when-not/alternatives as a tool description gets.

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