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

Annotations already cover read-only, idempotent, closed-world, non-destructive traits, and the description goes further: output is 'not a diagnosis', rules are explainable observed-code, safety escalations exist, prices are dated public estimates with distinct scopes/source years and no 2026 adjustment, and there is a shared free daily allowance (rate limit) with 'no network or model'. This is genuinely useful behavioral context beyond the structured fields.

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 purpose is front-loaded and every sentence carries information, but the text is dense and repetitive ('who does them' appears in both the first and second sentences, and 'fix options'/'options' is duplicated). Four tightly packed clauses make it harder to parse than necessary.

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 12-parameter, no-output-schema tool, the description covers output semantics (causes to investigate, not a diagnosis), pricing caveats and freshness, unknown-group handling, and the role of numeric inputs. Given there is no output schema, it does the heavy lifting well, though it does not describe the returned option/cost 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; the description nonetheless adds real meaning by clarifying that the numeric parameters 'price only agreed areas, designed storage or counted downspout sets' (i.e., they drive costing, not sizing) and that the soil check screens root-zone drainage. It also restates the 'omit unknown groups; [] means none observed' semantics shared with the schema.

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 likely causes of water pooling in a yard') plus the secondary outputs (fix options, who does them, dated cost estimates). It clearly delineates the 'in a yard' scope, which implicitly separates it from the sibling basement_water_cause, but it never names that sibling explicitly. Clear but lacking explicit sibling differentiation.

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?

Usage is only implied by the purpose statement; there is no explicit 'use this when...' routing and no alternative named, even though basement_water_cause is an obvious near-neighbor. The caveat 'returns likely causes to investigate, not a diagnosis' frames expectations but is not a selection guideline. Adequate only by inference.

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