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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the description's job is to add context, and it does: the source precedence ('local bank, then Unsplash/Pexels') tells the agent that the local curated bank is tried first and that external providers are a fallback, and 'verified, ready-to-use URLs' signals results are hotlink-ready with no download step. It does not disclose failure behavior or attribution requirements, which keeps it below 5.

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?

A single front-loaded sentence with no filler; every clause carries information. It is docked slightly because 'local bank' is an undefined internal term that leaves the reader guessing what that source is.

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?

Five optional params with full schema coverage and no output schema mean the description should at least sketch the return shape, and it does only minimally ('verified, ready-to-use URLs'). Missing are result shape/attribution obligations for Unsplash and Pexels, behavior when nothing matches, and any hint about how count interacts with the local bank fallback.

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%, so enum and default semantics for q, count, category, provider and orientation are already fully documented. The description adds only one nuance beyond the schema — that a local bank is consulted before the selectable Unsplash/Pexels providers — which is useful but doesn't elaborate on any individual parameter.

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 ('Stock photos') plus a quality claim ('verified, ready-to-use URLs'), which cleanly separates it from find_icon and find_video by resource type. It never names those siblings, so the differentiation is implicit rather than explicit.

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 sentence describes what the tool returns, not when to reach for it. There is no guidance on when to prefer find_image over find_video/find_icon, no prerequisite or preconditions, and no note about what to do when results are empty or the query is too vague.

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