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

Annotations already cover read-only, idempotent, open-world safety, but the description adds substantial context beyond them: LPA-boundary-scoped first pass, register-only candidate source, published point coordinates before boundary verification, heuristic scoring that ranks rather than excludes, unverified freshness, and the 50-record/1000m grid basis with unknown failure counts. This is exactly the kind of caveat an agent needs to caveat its answer.

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 labeled sections (Purpose, When to use, Returns, Limitations, Parameter guidance, Chaining) and nearly every sentence carries operational content. It is dense, however, and one sentence about the 'area application grid' reads as opaque internal jargon that costs more than it earns.

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 rich nested site_ref and an output schema, the description still supplies what structure cannot: source-of-truth limits, verification status of coordinates, grid sampling basis, and the site_ref chaining contract. An agent has everything needed to call it correctly and to hedge its conclusions appropriately.

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. The 'Parameter guidance' paragraph largely restates parameters already documented in schema descriptions (search_area, development_type, min_site_area_ha, max_flood_zone, transit distance, exclusion flags), and the ranking-not-exclusion nuance is also repeated in the schema descriptions. It reinforces but does not materially extend 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 and resource ('find and rank official English brownfield-register development-site candidates for an area') plus the enrichment step, and explicitly names sibling tools it is not (analyze_site, check_planning_constraints). An agent can distinguish it from all listed siblings without opening any schema.

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?

Provides an explicit 'When to use' with a concrete example brief ('brownfield residential sites in Salford over 0.25ha, outside Flood Zone 2/3...') and names the alternatives (analyze_site for a single known site, check_planning_constraints for raw constraints). Both positive and exclusion routing are present.

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