Aura DNA

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

Annotations already declare readOnlyHint and non-destructive behavior, so the safety profile is covered. The description adds genuine context beyond that: the output is educational guidance rather than a personal diagnosis, and the agent is told not to guess a season — a real behavioral constraint not in the schema.

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 short sentences, each doing distinct work: capability, empty-argument behavior, and usage constraint. Front-loaded with the action and nothing 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?

For a two-optional-parameter, read-only tool with no output schema, this is nearly sufficient. The only gap is the edge case of compareTo being passed without season, which the agent must 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 coverage is 0%, so the description must carry the load. It explains that 'season' is optional and what omission means, and that two seasons triggers comparison, which implicitly covers compareTo. But it never states whether compareTo alone is valid or what happens if only compareTo is supplied.

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?

Names concrete verbs (explain, compare, list) against a specific resource (named color seasons), and enumerates all three operating modes so the agent can predict behavior. It does not distinguish itself from the sibling find_season_essentials, which is the only missing piece.

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?

'Omit season to list available seasons' gives an explicit invocation condition for the zero-argument path, and the closing line sets a usage boundary (educational, not diagnostic). It stops short of naming alternatives such as find_season_essentials, so routing between the two is left implicit.

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?

The annotations already declare read-only, open-world, and non-destructive behavior. The description adds meaningful context beyond annotations: it returns real product links, images, and catalog prices, and explicitly clarifies that these are not live stock or a personal fit guarantee. This helps the agent set correct expectations about result freshness and limitations.

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 two concise sentences with no wasted words. The key purpose and return caveat are front-loaded, making it easy for an agent to parse quickly.

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 read-only search tool with annotations and no output schema, the description adequately explains the return format and caveats (links, images, prices, no live stock or fit guarantee). However, it omits important parameter details such as the category filter and result limit, which leaves the agent with incomplete operational 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 0%, so the description must compensate but only partially does. It references 'seasonal palette' and 'explicitly requested clothing range', which loosely map to the season and product parameters, but it does not explain the category or limit parameters, nor the enum values. The mapping is vague and leaves most parameter semantics undocumented.

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 verb and resource: 'Find curated clothing products' filtered by 'seasonal palette' and 'clothing range'. It clearly conveys the core purpose, though it does not explicitly differentiate itself from siblings such as explore_color_season.

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 by the phrase 'explicitly requested clothing range' and the seasonal palette focus, but there is no explicit guidance on when to choose this tool over alternatives like explore_color_season or get_offer. No exclusions or prerequisites are stated.

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 establish read-only, non-destructive, open-world behavior. The description adds useful context beyond that: it returns a normal website purchase link where permitted and does not create an order or charge a customer.

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?

Two sentences with no waste: the first establishes purpose and the second adds the key behavioral boundary around purchase links and no order creation.

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 tool with one parameter and no output schema, the description covers the main outcome and safety boundary. The remaining gap is that it does not explain the product enum semantics or response shape when the host does not permit the purchase-link workflow.

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 only parameter is product, with schema description coverage at 0%. The description says 'explicitly selected product' but does not explain what the men/women enum values mean or how they affect the returned offer.

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 and outcome: explaining the existing Aura DNA report, base price, required intake, and purchase link for a selected product. It distinguishes itself from report-listing/reading siblings by focusing on offer/pricing and purchase-link information, though 'Explain' is slightly less direct than 'get offer.'

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?

It implies usage for an explicitly selected product and notes the host-permitted workflow, which gives some context. However, it does not explicitly say when to use this instead of siblings like get_report or find_season_essentials.

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, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds useful domain context: the report must be 'owned' (an authorization scoping constraint) and clarifies it does not generate or purchase reports. It could go further on error behavior for non-owned reports, but it adds real value 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?

Two short sentences with zero waste. The primary capability is front-loaded, followed immediately by the parameter source and the negative constraint.

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, one-parameter tool with no output schema, the description is complete enough: it names the return contents (status, section index, resume link), explains where to get the identifier, and rules out report generation/purchase. Nothing essential for correct invocation is missing.

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 0%, so the description must carry parameter meaning. It does so by explaining that orderId comes from list_reports, which the schema (which only defines UUID format and pattern) cannot convey. The description does not explain what happens with an invalid or non-owned orderId, but the provenance guidance is the key missing piece and it is provided.

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 (read) and resource (one owned report) and enumerates what is returned: status, section index, and resume link. This clearly distinguishes it from siblings list_reports and get_report_section.

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 use an orderId from list_reports, giving the agent the correct source for the required identifier, and adds a negative constraint ('does not generate or purchase a report'). It does not explicitly mention get_report_section as the alternative for reading section content, but the 'available section index' phrasing implies the routing.

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 and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior: an ownership requirement on the report and an explicit rule that missing images and historical answers must not be invented or regenerated — a constraint an agent would otherwise violate. It does not describe response shape or what an empty/missing section looks like.

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 short sentences, front-loaded with the action and content scope, followed by the precondition and the constraint. No filler; the only cost is that the section enumeration and the no-invention rule are packed tightly without connective explanation.

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 read-only tool with two parameters and no output schema, the description covers what is returned (section content types), the access precondition, and the integrity constraint. The notable remaining gap is that without an output schema, nothing tells the agent the shape of a returned section or how a missing section is signalled.

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 0%, and while sectionId's enum values are partly echoed in the description (palette, hair, best-version, plan), the mapping is loose and most of the 15 enum values are unspecified. orderId is only obliquely explained via 'requires an owned report'; the description never says the ID refers to the report/order, which is exactly the missing semantic.

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 ('Read') and resource ('a selected saved section') and enumerates representative section content (palette, style, hair, Best Version, plan), which lets an agent distinguish this from the broader get_report sibling. It stops short of naming get_report directly, so differentiation is inferred rather than stated.

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?

'Requires an owned report' gives one hard precondition, and the section list implies this is the single-section alternative to fetching a whole report. There is no explicit 'use this instead of get_report when...' routing and no guidance on error behavior when the report is not owned.

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, destructiveHint=false, and openWorldHint=false, so the safety profile is clear. The description adds meaningful context about which reports appear in the result set (accessible paid reports, including those awaiting intake or processing) and how to handle multiple matches, though it omits pagination behavior.

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?

Two sentences, front-loaded with the core action and scope, followed by a practical selection rule. No filler or repetition.

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?

Covers purpose, scope, and multi-result handling well enough for a simple read-only list tool. The missing piece is pagination semantics for the page parameter, which matters because neither schema nor description explains it and there is no output 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?

Schema description coverage is 0%, so the description must compensate for the undocumented page parameter. It says nothing about pagination, page size, or limits, leaving the sole optional parameter unexplained.

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 ('List ... accessible paid reports') and clarifies scope by including reports awaiting intake or processing. It does not explicitly name or contrast with the sibling get_report, but the list-vs-get distinction is 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?

Provides a useful handling rule ('Ask the customer to select if more than one report could apply') for ambiguous results. However, it does not explain when to use this tool instead of get_report or get_report_section, leaving the primary routing decision implicit.

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