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

Annotations declare readOnlyHint=false, openWorldHint=true and idempotentHint=false; the description adds non-obvious behavior: fair-use cap per key per day, cost model for filing, 20–90s latency, and the instruction not to invent notice details. It doesn't explain what the non-readonly write actually persists (a scan record), but the disclosure is well beyond the annotation baseline.

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?

Front-loaded with the resource and outcome, then cost/quota, then input requirement and latency, closing with the anti-hallucination instruction. Every sentence carries distinct, needed information with no filler.

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, the description adequately summarizes the return (issuer, contravention, grounds, draft appeal) and explicitly mandates reporting exactly what the tool returns, covering the key completeness gap for an AI-facing notice scanner. Minor omissions (force parameter meaning, what non-readonly state change occurs) keep it just below a 5.

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 80%, so the schema documents image_url, image_base64 and content_type on its own. The description usefully clarifies that image_url OR image_base64 (one of two) is required, but says nothing about force or file_name, leaving gaps. Baseline 3 applies when the schema carries most parameter meaning.

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?

States a specific verb (scan/check) and resource (UK parking ticket, PCN, bus lane, ULEZ/CAZ notice) plus the full value chain: read, identify issuer/contravention, find grounds, draft appeal. This is clearly distinguishable from siblings like get_notice (retrieve) and file_appeal (submit).

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?

Explains the workflow context (checking is free, filing costs £7.99 or is plan-covered) which implicitly routes the agent to check before file_appeal, and specifies that image_url OR image_base64 must be provided. It does not explicitly contrast with get_notice or list_my_notices, so it falls short of the 'when-not' bar.

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