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

Annotations only say readOnly/idempotent/non-destructive; the description adds the substantive behavioural facts: the checklist is unassessed, there is no compliance or safety-clear statement, no storeys-to-height substitution, no regime equivalence, and the response contains empty legacy triggered/critical arrays with an unknown critical count. It also discloses the chaining contract (site_ref returned and passed unchanged to reuse canonical site, coordinates, boundary confidence, LPA, evidence links, project context).

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?

Labelled segments (Purpose / When to use / Returns / Limitations / Parameter guidance / Chaining) make it scannable and front-load the definition. It is dense and each block carries information, though the 'Returns' sentence is a long clause chain that takes a second pass to parse.

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 10-parameter tool with a deeply nested site_ref object and an output schema, the description covers the pieces the schema cannot: the non-determinative nature of the output, the limitation set, and the site_ref chaining requirement. With an output schema present it correctly does not attempt to document return field structure in detail.

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 100%, so the baseline is 3, but the 'Parameter guidance' paragraph adds real value: supply the brief, actual measured height with height_basis, explicit proposed_storeys, units and works_type 'where known', and it names what the caller must still bring (document edition, application/work dates, transitions). This shapes input choices rather than restating field text.

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 and resource ('prepare an England building-control review checklist') and immediately bounds scope with 'without determining applicable requirements or compliance.' The domain framing (fire, structure, ventilation, energy, access, overheating, BSR) is specific enough to separate it from prepare_heritage_review / prepare_biodiversity_review / prepare_sequential_review.

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?

Explicit 'When to use' clause pins it to feasibility/RIBA Stage 1-2 and lists the review topics it covers, and 'Limitations' plus 'Second-staircase height and higher-risk-building storeys are separate checks' tells the agent where the boundary lies. It stops short of naming sibling tools it should be preferred over, so the routing is by domain boundary rather than by explicit alternative.

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