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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint), and the description still adds real substance: a sealed reproducible receipt with per-quantity formula, units, inputs and uncertainty, 'conjecture' labelling for intelligence-bound quantities, GET-only access, and the 'Not a price' caveat. It does not describe failure modes or what 'sealed' verification requires, which is left to verify_receipt.

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?

Dense but front-loaded: the core action comes first, followed by the output contract and then the constraints (provenance binding, conjecture labelling, not-a-price, free rail). A few fragments ("Not a price. Free rail.") are terse to the point of being cryptic, but no sentence is filler.

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 shape needn't be restated, and the description correctly focuses on inputs, provenance binding, and interpretive caveats. The main remaining gap is the internal structure of the required `site` object given 0% schema coverage and a nested open object, which the description gestures at but does not pin down.

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% and the `site` parameter is an open object with additionalProperties=true, so the schema conveys almost nothing. The description partly compensates by naming the vef-site/0.1 component groups the site object is expected to contain, but it gives no field-level naming, required-vs-optional detail, or validation rules, so an agent still cannot construct a valid `site` from the 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 ("Value a site's ecological complexity") and scopes it with a named schema version plus the component set (D-Score components, habitat patches and links, optional GSIP soil indicators, NPP, temperature). It reads as clearly distinct from verify_receipt or explain_valuation, but it never names a sibling to sharpen the boundary.

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 condition for bind_vergecommon=true is given (reads a named VergeCommon public project as provenance), which is genuine when-to-use guidance for that parameter. However, there is no statement of when to call this versus describe_method, explain_valuation, or simulate_pool, so routing must be inferred from the name alone.

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