Measured Size

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

Goes well beyond the annotations by disclosing output behavior (confidence badge and reason per size), the out-of-range path (states it doesn't carry her size and why, e.g. bands start at 34 or cups stop at DD), and the closest_made field with an instruction to pass it on rather than guess. That is exactly the edge-case guidance an agent needs and annotations do not provide.

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?

Three sentences, front-loaded with the core definition before the usage trigger and the fallback. Dense but every clause carries information; the parenthetical example is the only slightly heavy element.

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?

No output schema exists, and the description compensates by naming the returned elements (size in brand labels, confidence, reason, closest_made) and the failure mode. For a 4-param read-only lookup, an agent has everything needed to call it and interpret the answer.

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 adds real meaning by explaining that brand matches a shopper-written name and that results are interpreted in the brand's own lettering, which the schema's field descriptions do not convey.

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: her size at one named brand, expressed in that brand's own labels, with a worked example (32E at UK-lettered brand for a US 32DDD). This clearly separates it from bra_size_from_measurements (no brand) and translate_bra_size (label conversion only).

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 this when a shopper names a brand" gives a clear trigger, and it explicitly routes to list_bra_brands when the brand isn't found. It does not explicitly contrast with bra_size_from_measurements or translate_bra_size, but the brand condition implicitly selects this tool.

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

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

Annotations already declare a safe, idempotent, closed-world read, so the description's job is to add operational context. It does: the response carries a confidence badge and a reason that must be passed on, and refused measurements should be relayed with the given reason. That is real behavioral guidance beyond the annotations.

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 output list and the usage condition are front-loaded across a compact set of sentences, each carrying information. Slightly dense in the opening enumeration, but nothing is padding.

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?

With no output schema, the description must describe the return, and it does: size variants plus a confidence badge and reason, along with how to handle refusals. It is close to complete for this tool's complexity, though it says little about ambiguous or edge-case measurement handling.

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 underbust, bust, and unit are fully documented in the schema with instructions and an enum. The description only restates 'inches or cm, decimals allowed', which duplicates the schema rather than adding format or validation detail. Baseline 3 is correct.

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?

The description states a specific transformation (measurements in, bra size out) and enumerates the exact outputs: base US size, sister sizes, UK, EU/French, and letter size. It implicitly separates itself from bra_size_at_brand via 'wants her size in general', but never names the sibling explicitly.

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 this when a shopper gives her measurements and wants her size in general' gives a clear triggering context, and the 'in general' phrasing contrasts with the brand-specific sibling. It also covers the refusal case, though it stops short of naming alternatives outright.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds useful content context (that records include aliases and a last-researched timestamp), but says nothing about ordering, pagination, or result size.

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-loads the resource and its field contents, then a second sentence for usage. The field enumeration is dense but each item informs what the tool returns; no 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?

With no output schema, the description usefully enumerates the fields returned, which is exactly what an agent needs here. A note on result ordering/size would round it out, but coverage is strong for a simple list tool.

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 100% and the single optional 'q' parameter is fully documented in the schema. The description does not mention filtering at all, so it adds nothing beyond the schema; baseline 3 applies.

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 (list/research brands) and resource (brands), and enumerates the record contents (aliases, sizing system, cup letters, ranges, chart on file, last-researched date). It is clearly the reference/catalog tool, distinguishable from the three sibling sizing tools.

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?

Explicitly says to 'find a brand's name before the other tools' and to 'say which brands are covered,' routing the agent relative to siblings. No explicit when-not or exclusion of the other tools, but the context is clear.

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

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

Annotations cover safety (readOnly, idempotent, non-destructive), and the description goes further by disclosing the output quality ceiling ('rated no higher than Good Match'), a consumer-facing instruction ('tell her so'), and three concrete refusal cases (letter sizes, missing labels, letter-size-only brands) with reasons. That is unusually rich failure-mode disclosure for a read tool.

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 most important constraint (no measurements → use this) is front-loaded, and the refusal list is compact. The closing clause 'with the reason' is grammatically tangled with the preceding enumeration, making the refusal sentence slightly harder to parse than the rest.

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?

With no output schema, the description carries the return-value burden and does so: it tells the agent the translated size is capped at Good Match, must be communicated to the shopper, and that failures return explanations. An agent can call this and interpret the result correctly without further information.

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 all three parameters are already documented at full fidelity, giving a baseline of 3. The description reinforces the from/to relationship and that 'size' is as from_brand labels it, but adds no syntax or format detail beyond the schema's own descriptions and examples.

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 ('translate a band and cup size... into another brand's label') with a concrete example (34DD at Wacoal → Curvy Kate). It also pins the mechanism ('through Measured Size's base size'), which distinguishes it from bra_size_from_measurements and bra_size_at_brand.

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?

Gives an explicit gate: 'Use this only when the shopper has no measurements; measurements give a better answer,' which routes the agent to bra_size_from_measurements and implicitly scopes out bra_size_at_brand. Nothing about when to select this tool is left to inference.

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