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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so safety behavior is covered by structured data. The description adds the output shape (total cost estimate and time hours), which is useful, but says nothing about whether the cost is currency-specific, region-specific, or how estimates are derived. An output schema exists, so the return-format mention is redundant rather than additive.

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?

Four short, front-loaded sentences, but the third sentence is not just wasted — it is wrong, describing non-existent inputs. The opening and the list_bundles pointer do earn their place.

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 computation tool with a full output schema, the description only needs to nail inputs, scope and output meaning — and it fails on inputs, listing the wrong fields entirely. An agent cannot reliably determine what to supply from this definition alone. The missing coverage of units (cm, FR dress size) is partially saved by the schema.

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?

The description names inputs that do not exist in the schema: 'alterations needed (hem, sides, sleeves)' and 'garment type' are not parameters, while the four actual required parameters (target_size, measurement_bust, measurement_waist, measurement_hips) go unmentioned. This is actively misleading rather than merely silent, despite the schema's 100% description coverage. An agent reading only the description would construct the wrong call.

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 (estimate) and resource (dress alteration cost and time) and narrows the scope with 'by alteration type'. It also distinguishes itself from the sea of calculate_* siblings by pointing at the 'textile-mode' bundle. However, it does not differentiate against the nearest siblings (calculate_fabric_needed, calculate_clothing_size_convert, calculate_shoe_size).

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 tailoring or wedding-dress budgeting' gives a use context, and it cross-references list_bundles for related calculators. There is no when-not guidance, no prerequisites, and no statement of how it differs from the other garment/textile calculators.

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