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

readOnlyHint=true is consistent with 'Finds', so no contradiction exists. Beyond the annotations, the description contributes real behavior: matching is conjunctive (every supplied word must appear) and objects are sized to their picture. It does not cover return shape or result limits, which keeps it off a 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?

It is a single sentence with no filler, and the core action is front-loaded. But the nested clauses and parenthetical ('which is as large as its picture') make it a run-on that is harder to parse than the content warrants.

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 and 0% schema description coverage, the description should describe what comes back (picture names? identifiers? how many?) and account for all three parameters. It leaves the return value and the `count` parameter entirely unaddressed, so an agent knows roughly what to send but not what it will receive.

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 0%, so the description must carry the load. It usefully explains the `kind` enum's two values (painting for a canvas, object for a prop) and clarifies `words` as an all-words-must-match filter, but `count` (1-20) is never mentioned or bounded anywhere in prose.

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 verb+resource ('Finds pictures') is concrete, and the description makes the matching rule ('words hold every word you give') and the two result kinds (paintings vs. everyday objects) explicit. However, the phrasing is oblique — 'whose words hold every word you give' takes effort to decode — and no sibling tool (e.g., textures, appearance, paint_faces) is named to delineate scope.

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?

Usage is implied rather than stated: pictures are found 'to hang,' 'for a canvas,' or 'for a prop,' which suggests the decorating/painting workflow. There is no explicit when-to-use or when-not, and no pointer to the alternative sibling tools that surface visual assets.

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