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

Annotations (readOnlyHint=false) correctly signal a mutating operation, and the description adds the key validation behavior: at least one caption is required or the request is rejected. Much of the deeper behavioral detail (silent font substitution with X-JE-Font-* headers, invalid colors reverting to defaults, stroke layering) lives in the schema rather than the description, but it is still available to the agent. The description uniquely contributes the rendered-style context but no side-effect, authentication, or rate-limit details.

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?

Two sentences plus a category tag, with zero filler. The first sentence front-loads verb, resource, and style; the second states the single cross-parameter validation rule that determines request success. Every element earns its place.

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 9-parameter tool, the description is complete enough because the schema covers every parameter in detail and annotations establish the safety profile. No output schema exists, but the expected result (the image with captions applied) is self-evident from the purpose statement. Minor gap: the description doesn't mention response shape or the output_format default behavior, but the schema already covers the latter.

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 100% and the schema descriptions are unusually rich (font fallback behavior, silent color reverts, stroke draw order, enum constraints, defaults). The description's only param-adjacent statement ('At least one of top_text/bottom_text is required') duplicates what top_text's schema description already states, so the description adds no net new parameter meaning. Baseline 3 applies since the schema does the heavy lifting.

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 uses a specific verb ('Add') with a clear resource ('caption text to an image') and distinctive style markers ('bold top and bottom... Impact-style font'), making the meme-generation purpose unmistakable. It differentiates from siblings like photo_watermark and photo_image_overlay through the top/bottom caption framing, though it never names an alternative explicitly.

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 intended use case is implied by the 'Meme Generator' framing, so an agent can reasonably infer when to invoke it. However, with 100+ siblings including overlapping tools like photo_editor, photo_watermark, and photo_image_overlay, there is no explicit when-to-use/when-not-to-use guidance or named alternatives to route around confusion.

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