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

Annotations already fully declare the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds the return payload ('Returns m³ and bag count'), which is mildly useful even though an output schema exists, but discloses nothing about bag-volume assumptions, rounding, or units handling.

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?

Compact and front-loaded: the computation and return values come first, followed by usage and a cross-reference. Every sentence is short, though the inaccurate input list is wasted space that should have matched the schema.

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 three-parameter calculator with full schema coverage and an output schema, the description is roughly sufficient on returns and safety. Its completeness is undermined by the fabricated input list (area, bag volume) that contradicts the actual schema, leaving the agent to reconcile a mismatch.

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 covers all three parameters at 100%, which would normally be a baseline 3, but the description actively misstates them: it lists 'area, depth, bag volume' while the schema actually defines length_m, width_m, and depth_cm. Only 'depth' maps to a real parameter, so the description misleads rather than informs.

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+resource: computes soil volume in m³ plus bag count for a garden bed. This is distinguishable from siblings like calculate_raised_bed_soil or calculate_compost_volume, though it never names them. Purpose is clear without being explicitly differentiated.

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?

'Use for gardening' is a trivial restatement with no when/when-not guidance and no comparison to the nearest siblings (raised bed soil, compost volume, garden water needs). The 'See list_bundles' pointer routes to a discovery tool, not to the alternative the agent should choose between.

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