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

Despite readOnlyHint=true, the description goes well beyond the annotations by disclosing that the return is an editor link (never an image source), that captions may come back with server-inserted line breaks, where the author handle is placed and how corners are claimed, and that captions are auto-fit and coloured. It also says what the returned picture contains (watermark, 1200 px, or 800 px preview) — none of which the annotations convey.

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?

The core requirement is front-loaded in the first sentence, but the body is a dense run-on with deeply nested parentheses covering caption re-fitting, handle placement and a curl/pipe recipe. Nearly all content is useful, yet the packing makes it harder to scan than it needs to be.

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 13-parameter tool with no output schema, the description carries the return-value burden well: editor link, per-caption results, warnings, and the preview/final picture distinction with defaults. Only a few low-risk parameters (language, filter_strength) and the exact response item shape are left unaddressed.

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 62% schema coverage across 13 params, the description adds real meaning: the one-of constraint among template/image/image_url, the accepted image formats and size/pixel limits including the first-frame GIF rule, and the three caption placement modes (slot, classic position, x/y box fractions). It leaves language, filter_strength, preview and several nested fields to the schema.

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 first sentence gives a specific verb and resource ("Create a meme") and immediately constrains the source to exactly one of template, image or image_url. It also names the sibling get_template as the place to find slots, so an agent can distinguish this creation tool from the discovery tools without opening a schema.

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?

It states the mutually-exclusive source rule, tells the agent to consult get_template for slots, and explains which picture default applies to which source. It also gives a concrete when-to-use-a-shell workflow for files on disk instead of pasting base64. What's missing is any explicit when-not-to-use guidance relative to popular_templates/search_templates.

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