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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), yet the description adds non-obvious behavior: output is assembled from MCP tool outputs only, is not a signed planning statement, does not replace specialist reports, and deliberately preserves missing data rather than filling gaps with generic claims. That last disclosure materially changes how an agent should interpret and present the result.

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 a labeled Purpose, then When to use, Returns, Limitations, Parameters, Chaining — every section is scannable and earns its place. The Returns sentence partly duplicates the output schema, which is the only mild redundancy.

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 four-parameter tool with a nested site_ref and an output schema, the description covers purpose, selection criteria, grounding limitations, parameter intent, and the cross-tool chaining contract. Nothing an agent needs in order to call it correctly or interpret the draft is missing.

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 description goes further by telling the agent what to put in each field: full address/postcode, development_type, and optional proposed_description with intended use, height, scale, or works. It also explains the chaining contract for site_ref (pass unchanged to reuse canonical site, coordinates, boundary confidence, LPA, evidence links).

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 ('draft') and a concrete artifact ('grounded site description, constraints, accessibility, planning history, and policy-context sections for a D&A Statement or feasibility note'), plus the grounding source ('Atlasly source-backed tool outputs'). It explicitly names the sibling it is not ('use analyze_site when they only need a concise factual read'), so an agent can route between the two without opening a 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?

The 'When to use' clause gives both the trigger intents (D&A site context, planning statement background, site description, policy-context first draft) and the exclusion condition that selects the alternative tool. It also states the precondition of a 'known site', which is a real gating constraint.

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