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

With zero annotations provided, the description carries the full burden of disclosure and does so exceptionally well. It reveals the return format (PNG inline under 1MB, otherwise a 24-hour stored URL), auth requirement (signed-in account, 401 for anonymous), rate limit (20 images/hour), latency (tens of seconds), provider fallback chain, non-determinism, absence of seed/size control, and lack of permanent hosting. This is rich behavior context beyond any structured field.

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 description is long but every sentence earns its place given there are no annotations and no output schema to lean on. It is front-loaded with the core purpose, followed by return format, exclusions, alternatives, auth, rate limits, latency, and provider behavior. Minor redundancy exists between 'no two calls give identical output' and 'not automatically hosted anywhere permanent,' but both convey distinct information.

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 tool with no annotations and no output schema, the description is nearly complete: purpose, return format, retention, exclusions, alternative tool, auth requirements, rate limits, latency, provider variability, and determinism are all covered. Minor gaps include specific error responses beyond 401 and exact pricing for 'paid compute,' but these fall outside typical MCP description expectations.

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 the schema fully documents both prompt and negativePrompt, including the caveat that negativePrompt only works on the Replicate fallback. The description adds no parameter-specific semantics beyond reinforcing that provider variation exists, which the schema already notes. Baseline 3 is appropriate 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 first sentence states a specific verb and resource: 'Generate a new image from a text description with a diffusion model.' It further distinguishes itself by explicitly stating what it cannot do ('cannot edit, upscale or restyle a picture you already have') and naming compress_image as the sibling for existing files, so an agent can tell it apart from all three siblings without opening their schemas.

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 description explicitly guides routing: 'Use compress_image to re-encode or resize an existing file,' which covers the most likely confusion since both tools handle images. It gives clear when-not-to-use context ('invents an image from scratch'). However, it does not explicitly compare against generate_qr_code or split_image, leaving that differentiation to inference from tool names.

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