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

Annotations already cover readOnly/idempotent/openWorld/non-destructive, so the bar is low, yet the description adds genuinely useful non-structural facts: no account or credit required, duplicate plates collapse to one lookup, and prediction-based ranking is deliberately excluded. The only gap is what happens when a plate fails to resolve.

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?

Four short sentences, front-loaded with the core action and with no filler. Some phrasing is awkward and low-information ("Includes questions from free facts, comparison image and report links"), which slightly dilutes an otherwise tight block.

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?

An output schema exists, so return values need not be enumerated, and the description still adds auth posture, dedupe behaviour and the free-vs-detailed boundary. What is missing is failure handling and any hint about the cost of a call, both relevant for an openWorld tool with no credit requirement.

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 a single parameter and the schema already giving format guidance ("UK registration plate, any spacing or case"), the description adds the cardinality constraint ("exactly two plates") and the dedupe rule, which are semantic behaviours the schema's min/max items alone do not explain. Limited headroom remains for a single-param tool.

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 concrete verb and resource ("Compare ... for exactly two plates") and enumerates the compared facets: identity, status and latest MOT test. It also bounds scope against the paid sibling by saying next-MOT estimates and likely repairs "stay in the detailed report". The word "projections" is jargon that is never defined, which keeps it just short of a 5.

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?

Usage is implied rather than stated: the description makes clear this is the free two-plate comparison and that deeper analysis lives in "the detailed report", but it never names the actual alternatives (free_check, full_report, decode_plate) or says when a single-plate lookup should be used instead. It also does not say what to do when more than two vehicles need comparing.

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