Scento Perfume Compendium

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully structured. The description adds nothing behavioral beyond that (no pagination behavior, no result-size or ranking caveats), which is acceptable given the rich annotations but earns no extra credit.

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?

A single sentence with no filler, front-loading the verb and the resource. Every clause earns its place by naming the entity kinds and the search axes.

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 an output schema present and annotations carrying the safety profile, the definition is nearly complete for a read-only search. The only meaningful gap is routing guidance relative to the numerous sibling tools, which the description leaves for the agent to infer.

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%, so all four parameters are already documented in the schema, including the 'q' search axes, 'kind' enum, 'lang' enum, and 'continuation'. The description's mention of name/house/note/mood word largely restates the 'q' schema text and adds no format or syntax detail, so the baseline of 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?

The description gives a specific verb ('Find') and resource set ('perfumes, houses and raw materials in the Scento Compendium'), plus the retrieval axes (name, house, note, mood word). It clearly differentiates the tool as a lookup/search, but never names which sibling tools it supersedes or complements, so sibling differentiation is left implicit.

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 word 'Find'; there is no explicit when-to-use guidance and no mention of alternatives such as material-match, note-portrait, or house-portrait, which plausibly overlap with this tool's search surface. An agent must infer that this is the general name/note lookup versus the specialized portrait tools.

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=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is clear. The description adds only that the tool returns Scento's own family system and that single-family results include subfamilies and exemplars; it does not add further behavioral context such as error handling or response shape.

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 description is a single concise sentence with no wasted words. It is front-loaded around the resource, though its brevity leaves some ambiguity about the exact action and alternatives.

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 simple read-only, idempotent, non-destructive tool with full schema coverage and an output schema, the description is minimally adequate. However, it lacks guidance on when to choose this tool over sibling tools, which is a meaningful gap in context.

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%, so the lang and family parameters are already well documented in the schema. The description reinforces the whole-map versus single-family distinction but does not add syntax, format, or constraints beyond what the schema provides.

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 names a specific resource: Scento's fragrance-family system, and clarifies that it can return either the whole map or a single family with subfamilies and exemplars. It does not explicitly distinguish this from siblings such as perfumery-lexicon or scent-neighbours, so it falls short of a 5.

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 description implies two modes via the family parameter, but it does not say when to use this tool rather than siblings like perfumery-lexicon or material-match. There is no explicit when/when-not guidance or prerequisite information.

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=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered elsewhere. The description adds nothing behavioral beyond that — no note on data source, coverage limits, or freshness — so it is essentially a restatement of the title's promise.

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?

A single short sentence with no filler, and the payload fields are front-loaded. It is arguably over-terse rather than wasteful, since a fragment with no verb leaves the operation implicit, but every word earns its 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?

An output schema exists and both parameters are fully documented, so the description need not explain return values. For a low-complexity read tool the only real gap is the absence of sibling routing, which leaves it adequate but not complete.

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%: 'house' is documented with concrete examples and 'lang' explains the enum's effect on links. The description contributes no additional parameter meaning, which is the expected baseline when the schema already does this work.

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 names a specific resource (a perfume house) and enumerates exactly what the portrait contains: origin, founding year, style, and signature perfumes. It is clear what data comes back, but it uses a noun phrase with no verb and never contrasts itself with the adjacent portrait tools (perfume-portrait, note-portrait), so an agent must infer the distinction.

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?

There is no statement of when to reach for this tool versus perfume-portrait, note-portrait, or compendium-search, and no prerequisites or exclusions are given. The agent gets a description of the payload but no routing guidance at all.

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=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds no behavioral context (no pagination/continuation behavior, no result scope beyond 'articles'), so it neither adds value nor contradicts; baseline 3 fits.

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?

A single short sentence with no filler; the query domain is front-loaded. It is arguably under-specified rather than wasteful, but nothing is redundant.

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?

Annotations and an output schema carry the safety and return-value burden, so the description need not explain results. However, for a search tool with a search-like sibling, omitting any routing guidance leaves a real gap for correct selection.

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%, including per-parameter descriptions and examples for q and an explanation of lang and continuation. The description restates the q domain but adds nothing beyond the schema, so the baseline 3 is appropriate.

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 plus title state a clear resource and intent: journal articles on a perfume, house, material or topic, retrieved by search. The resource ('Scento journal articles') is specific, but it gives no differentiation from the sibling compendium-search, which likely has overlapping scope. Clear but not distinguishing.

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?

There is no when-to-use/when-not guidance and no mention of alternatives. With a sibling compendium-search present, an agent has no signal for choosing between two search-like tools. Only the query scope ('on a perfume, house, material or topic') implies usage.

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, non-destructive and closed-world, so the safety profile is covered. The description adds genuine behavioral detail by specifying AND semantics ('every material given' must all be present) and optional tier scoping, which is more than the annotations supply but still thin.

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?

A single tight sentence that front-loads the core matching behavior and tucks the tier qualifier after it. No filler, though it is arguably under-specified rather than optimally sized.

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 values need not be explained, and the read-only annotations cover safety. What remains missing is routing guidance versus the many sibling tools and any note on result limits or pagination, leaving the definition adequate but not complete.

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%, so every parameter including lang, tier, family, materials and continuation is already documented. The description only reinforces the conjunction logic of materials and the optional tier constraint, adding marginal value over 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 resource (perfumes) and matching criterion (contain every material given), plus an optional tier scope. It is a clear noun phrase rather than verb+resource and it does not distinguish itself from near neighbours like note-portrait or perfume-portrait, so it stops short of a 5.

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?

There is no explicit when-to-use or when-not-to-use guidance, and no alternative tool is named despite a crowded sibling set (note-portrait, perfume-contrast, scent-neighbours). The agent must infer the usage context from the purpose statement alone.

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, non-destructive, and closed-world, so the safety profile is fully covered. The description adds only that the answer is descriptive rather than operational, and says nothing about response shape, limits, or lookup failure behavior, so no extra credit is earned beyond the annotation baseline.

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?

A single compact sentence with no filler and the key concept (note/raw material) front-loaded. It is well sized, though it reads as a content summary rather than a directive statement of what the tool does.

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 values need not be described, and annotations fully cover the safety profile while the schema documents both parameters. The only real shortfall is the absence of routing guidance relative to sibling tools, which is handled elsewhere.

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%, with the material parameter carrying examples (vetiver, orris, ambroxan, pink pepper) and the lang enum documented with its default. The description's phrase 'a note or raw material' merely echoes the schema, so the 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?

The description names a specific resource (a note or raw material) and enumerates the content it returns: identity, origin, and skin behavior. It clearly differs from generic search tools, but as a noun-phrase fragment it never states the verb and doesn't distinguish itself from near-siblings like material-match or perfume-portrait.

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?

There is no when-to-use guidance and no named alternative, even though the sibling list contains directly adjacent tools (material-match, perfume-portrait, house-portrait) that an agent must choose between. The agent is left to infer the routing decision entirely.

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 safety and side-effect profile are fully covered. The description adds useful output-shape context ("with a line on each"), but says nothing about list length, ordering logic, or how results relate to the requested occasion.

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?

A single well-formed sentence with no filler, front-loading the deliverable ("short edit of perfumes") and appending the output detail. Nothing is wasted and nothing is buried.

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 values need not be explained, and the schema fully documents all parameters. However, for a tool embedded in a large sibling ecosystem with overlapping purpose (wardrobe-composer, compendium-search), the absence of any routing guidance leaves a real gap.

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% with all three parameters documented and enum-constrained, so the baseline is 3. The description adds only one marginal clarification, that "occasion" may also be read as season or climate, which explains enum values like summer-days and cold-weather but does not cover lang or gender_lean.

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 concrete deliverable: a short curated list of perfumes keyed to an occasion, season, or climate, each with an accompanying line. It is specific about output shape but uses the jargon term "edit" without definition and never distinguishes itself from siblings like wardrobe-composer or compendium-search.

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?

There is no when-to-use guidance, no exclusions, and no mention of any alternative tool. An agent choosing among twelve siblings receives no signal about when occasion-edit is the right pick versus compendium-search or wardrobe-composer.

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, non-destructive and closed-world, so the safety profile is fully covered. The description adds the comparison dimensions used for the output, which is useful, but says nothing about latency, limits, or what happens on partial name matches.

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?

A single front-loaded sentence with no filler; the constraint and the comparison axes both appear immediately.

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 values need not be explained, and the annotations carry the full safety profile. For a simple two-parameter read-only comparison tool, the description plus schema leaves nothing an agent needs to call it correctly.

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 both parameters are documented in structured data and the baseline is 3. The 'two to four' phrasing merely restates the schema's minItems/maxItems, and the lang parameter is not mentioned at all, so no meaning is added beyond 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?

The description gives a specific verb ('set side by side') and resource ('perfumes'), and enumerates the comparison axes (family, pyramid, character, season). This distinguishes it reasonably from single-perfume siblings like perfume-portrait, though it never names an alternative 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?

The phrase 'two to four perfumes side by side' implies the comparison scenario, so intended use is inferable. However, there is no statement of when to prefer this over scent-neighbours or perfume-portrait, and no prerequisites or exclusions are given.

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=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered structurally. The description adds useful context about what the portrait contains, but says nothing about fuzzy name resolution, ambiguity between houses, or link-language behavior beyond what the schema notes.

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?

A single front-loaded sentence with no filler; the resource and its returned components come first. It is appropriately short, though the phrase 'when it wears best' is slightly looser than a crisp facet label.

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 an output schema present, return values need not be spelled out, and annotations cover the safety profile, so the description's remaining job is scope and content preview, which it does. Missing only explicit routing against the many sibling portrait/search tools.

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%: the 'perfume' and 'lang' parameters are fully documented in the schema, including the name-vs-slug formats and the enum of link languages. The description adds no parameter detail, so the 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 the specific resource (one perfume) and enumerates the returned facets (pyramid, Scento family, character, occasions), so the agent knows it is a holistic single-perfume lookup rather than a note- or house-level one. It does not explicitly name siblings like note-portrait or house-portrait to draw the boundary, but the scope is unambiguous.

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?

There is no when-to-use or when-not-to-use guidance and no mention of alternatives such as perfume-contrast, scent-neighbours, or note-portrait. The phrase 'when it wears best' describes output content, not invocation context, so the agent must infer selection 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.

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 and side-effect profile is fully covered for a pure lookup. The description adds no behavioral context beyond the annotations, but for a deterministic dictionary lookup there is little left to disclose; a 3 reflects credit for the fully-covering annotations with no added description value.

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?

A single front-loaded sentence with zero wasted words and the examples placed immediately after the core statement. It is a noun phrase rather than a full sentence, which is slightly less informative than a compact verb-led statement, but nothing is padded.

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 an output schema present, the description need not explain return values, and annotations cover the safety profile; the two-parameter schema is fully self-documenting. What remains missing is only minor usage routing against the eleven siblings, which the description assumes the agent can infer.

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 both parameters are documented in the schema, including the subtle rule that lang controls the language of scento.com links while answers stay in English. The description only repeats example terms already present in the schema's term description, so the 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?

The description states a specific resource (a perfumery term) and what is returned (its plain-language meaning), with concrete examples (sillage, chypre, fougère, EDP vs EDT) that make the tool's domain unambiguous. It does not explicitly differentiate itself from siblings like compendium-search or material-match, but the lexicon-lookup nature is self-evident enough to route correctly.

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 implied rather than stated: the tool is for interpreting terminology, not for searching perfumes or houses. There is no explicit when/when-not guidance and no named alternative (e.g., use compendium-search for products rather than definitions), so an agent must infer the boundary from sibling names alone.

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, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds that shared materials are named in the output, but says nothing about list size, paging semantics, or how 'structure' is measured.

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?

A single compact sentence with the core resource front-loaded and the output detail trailing. No filler or redundancy.

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 values need not be explained, and the schema documents all four parameters. However, the description omits any usage context or sibling disambiguation, which matters for a tool surrounded by eleven related discovery tools.

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%, including the lang enum explanation, same_house scoping, and the continuation parameter for paging. The description adds no parameter meaning beyond the schema, so the 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?

The description states a specific resource ('perfumes that share the most structure with a given one') and an output detail ('shared materials named'), so an agent knows it retrieves structurally similar perfumes. It does not differentiate itself from near siblings like family-map, material-match, or perfume-contrast, leaving the boundary fuzzy.

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?

No when-to-use guidance, no prerequisites, and no mention of an alternative among the 12 sibling tools. The 'continuation' parameter hints at paging through a result list but the description never says so explicitly.

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 read-only, idempotent, closed-world, non-destructive profile, so the safety burden is covered. The description adds only the curation trait that results span 'different moments,' which is modest extra context; it says nothing about how overlaps with avoid/size are resolved.

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?

A single front-loaded sentence with zero filler, clearly stating output size and the personalization anchor. It is efficient, though its brevity borders on under-specification given the available space.

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 an output schema present and all four parameters fully described in the schema, the description need not explain return values or parameter formats. It remains incomplete on routing against similar sibling tools, which is the one thing structured fields cannot supply.

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%, so the schema already documents loves, avoid, size, and lang with defaults, bounds, and enum. The description's 'built around what the person already loves' and 'three to five' loosely echo two parameters but add no syntax or format detail beyond the schema, which is the expected baseline.

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 concrete output (three to five perfumes) and the curation logic (cover different moments, built around what the person already loves), so an agent grasps the purpose immediately. It does not, however, differentiate itself from plausibly overlapping siblings such as occasion-edit or scent-neighbours.

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?

There is no when-to-use guidance, no exclusions, and no named alternative. The agent must infer that this tool is for building a multi-perfume set from existing favorites rather than for a single lookup or edit, but nothing in the text says so explicitly.

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