Image roulette

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

The description adds non-obvious behavioral signals beyond annotations: the tool returns a single result, the selection is random/non-deterministic, and it is 'honest about how it was chosen.' This complements the readOnlyHint and aligns with idempotentHint=false; no contradiction is present.

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?

One deliberately hand-crafted sentence fits the whole essence of the tool: randomness, scope, licensing, and the "one" pick. There is no filler, and the key behavioral distinction 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?

For a simple read-only tool the description is relatively complete, but it lacks an output schema and does not describe what shape the result takes (URL, metadata, etc.). The seed parameter remains a mystery, so a fully correct call from a cold start is still uncertain.

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?

With 0% schema description coverage, the description needs to carry the burden of explaining all parameters. It loosely maps 'matching a topic' to query and 'openly-licensed' to license, but it never explains the seed parameter, allowed license values, or the relationship between seed and randomness.

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 clearly identifies a distinct operation: returning a single random, openly-licensed image matching a topic. 'One pick' and 'random' distinguish it from the adjacent find_images tool, so there is little ambiguity about what this tool does.

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?

The use case is implied by 'serendipity' and 'one pick' — use when you want a chance discovery rather than a broad search. However, it does not explicitly name when to use this vs. find_images or give any exclusions/preconditions, so the agent must infer this distinction.

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