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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds that it 'never submits DWT records', which reinforces the read-only nature beyond annotations. It also states the scope is 'England phase 1 only' and 'returns phase-1 scope/readiness, findings and evidence', which is useful. No contradiction with annotations. The description does not detail side effects, but given the annotations, this is adequate.

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 a single dense paragraph but front-loads the tool's purpose and key constraint ('FREE... for England phase 1'). It avoids fluff and every sentence adds value: scope condition, required inputs, return value, and exclusions. It could be slightly reorganized for readability but is efficient, not overly verbose.

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?

The tool is moderately complex with multiple nested parameters, but the description covers the main inputs, scope, and exclusions. With an output schema present, the description need not explain return values in detail. The description handles the key contextual aspects: the tool is read-only, returns evidence, and is limited to England phase-1. Minor gaps include not detailing how findings are structured or how to handle edge cases like null authorisation, but the output schema and param descriptions compensate. Overall, it is complete enough for selection and invocation.

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 0%, so the description must compensate for the lack of per-parameter documentation. The description lists all key inputs: 'receiving authorisation, whether controlled waste is received, reporting-method readiness, and optionally an as-of date.' This aligns with the five nested properties, providing semantic meaning beyond parameter names. It also gives guidance on using 'as-of date' for optionality. Since there are no enums with descriptions, this compensates well.

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 clearly states a specific purpose: checking receiving-site readiness for England phase 1 of digital waste tracking, with a specific verb 'select' and resource 'receiving-site'. It explicitly distinguishes from sibling tools by naming exclusions ('Do NOT use for carrier registration or permit-change comparison'). It also states a clear scope condition ('only when the question is whether...') and key constraints (never submits DWT records).

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 provides clear guidance on when to use the tool: only for checking receiving-site readiness with the specific phase-1 scope. It also gives explicit 'Do NOT use' instructions for carrier registration and permit-change comparison, which map to siblings like waste_carrier_broker_dealer_preflight and waste_permit_change_preflight. However, it does not enumerate all sibling alternatives nor elaborate on edge cases, but the primary exclusion is clear.

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