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

Adds non-schema behavior: 20–90 second latency, fair-use daily cap, pricing, and an explicit anti-hallucination instruction to report exactly what the tool returns. Annotations already carry readOnly/destructive flags, so the description adds meaningful context rather than repeating them.

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 front-loaded with the core action and includes necessary operational details like input format, latency, and cost. It is slightly dense with pricing/plan information, but each sentence serves agent decision-making.

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?

Despite lacking an output schema, the description states that results include issuer, contravention, grounds, and a drafted appeal, and warns not to invent details. It covers input requirements, timing, and cost; minor gaps remain around exact response structure and mutual exclusivity of image inputs.

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?

The input schema covers most parameters (80%) with descriptions for image_url, content_type, image_base64, and force; the description reinforces 'image_url OR image_base64' but adds little beyond that. file_name is left undocumented in both the description and 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 description names a concrete verb+resource: upload a UK parking ticket/PCN and have AppealGo read it, identify the issuer and contravention, and draft grounds/appeal. This clearly distinguishes it from siblings like get_notice, explain_contravention_code, and file_appeal.

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?

Gives clear context: use when the user has a photo/PDF of a UK notice to check; instructs the agent to provide image_url or image_base64 and notes timing, cost, and free-use cap. It does not explicitly name sibling alternatives or when-not conditions, so it falls short of a 5.

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