AirShelf Catalog

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

Beyond the readOnlyHint annotation, the description discloses slug normalization, per-item result structure (canonical_name, spec_absence_note), the need to branch on commercial_data.actionable for stale data, not_found behavior with did_you_mean, and provenance semantics. This is rich, non-obvious behavioral context with no contradictions.

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 front-loaded with the core purpose, then layers details logically. Every sentence contributes value—slug tolerance, result structure, stale-data handling, not_found behavior, provenance—and the length is justified by the tool's complexity.

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?

Given an output schema exists, the description still covers important runtime semantics: error cases (not_found, did_you_mean), data freshness (commercial_data.actionable), and per-item spec absence notes. This makes the tool fully understandable and actionable for an agent.

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% for both parameters, but the description adds meaning beyond the schema: slug case-insensitivity and dash tolerance, and clarifies that provenance 'adds the source page and source type already stored with each fact.' This goes beyond the schema's simple boolean description.

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 opens with a specific verb and resource: 'Compare 2-10 catalog products side-by-side on their datasheet specs.' It clearly distinguishes this from sibling tools like get_product by emphasizing multi-product comparison, and adds useful detail about slug flexibility.

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 provides clear context for when to use the tool (comparing 2-10 products) and notes that slugs come from search_catalog, implying a prerequisite. However, it does not explicitly name alternatives or state when *not* to use it, so it stops short of a 5.

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?

Beyond the readOnlyHint annotation, the description discloses behavioral traits: it states that stored processing stages are returned 'when available' (acknowledging potential absence) and that a golden-record field summary is 'always' returned. This provides useful expectations about variability and guarantees, adding value beyond the annotation.

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 sentences with no irrelevant content. The first sentence immediately states the core action, and the second sentence lays out return behavior. It is efficient and front-loaded, making it easy to parse.

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 tool with a single parameter, read-only annotations, and an output schema, the description covers the essential aspects: what it does, what it returns, and variability in processing stages. It does not explicitly discuss error cases or output structure, but the output schema covers returns. Overall, it is sufficiently complete for the tool's simplicity.

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 schema describes the single parameter 'slug' as 'Composite slug to explain,' which is 100% coverage. The tool description adds the context that this slug refers to a 'catalog row,' but does not elaborate on slug composition or format. Since schema coverage is high, the description meets the baseline without needing to compensate extensively.

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 clearly states the tool's function: 'Explain the evidence behind a catalog row.' This distinguishes it from sibling tools like get_product or find_products by focusing on evidence/provenance rather than retrieval or comparison. The additional detail about returning processing stages and a golden-record summary reinforces the specific purpose.

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 the tool is used when you need to understand how a catalog row was constructed, but it does not explicitly state when to use it over alternatives or provide exclusions. No sibling tools are mentioned in the description, so the agent must infer usage 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 provide readOnlyHint and openWorldHint, and the description adds substantial behavioral context beyond those: catalog-first then live discovery, status meanings ('no_match', 'disabled', 'rate_limited', 'unavailable'), verification categories ('catalog-candidate' vs 'live-unverified'), and market biases on cache and seller-page availability. No contradiction with 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 description is longer than average but well-structured: a purpose paragraph, sibling comparison, bulleted response fields, and market clarification. It is front-loaded with the core purpose and usage, and every section adds meaningful operational detail rather than 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 three parameters, several sibling tools, and an output schema, the description covers all essential behavioral aspects: candidates sources, status meanings, verification flags, receipt mapping, market semantics, and live discovery fallback. It is self-sufficient for an agent to select and invoke the tool 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% and each parameter already has a useful description, so baseline is 3. The tool description adds extra semantics by noting max 'each costs a live lookup; capped at 3' and market 'scopes the lookup cache' and that availability is not a stock guarantee, adding value beyond the schema alone.

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 'Discover candidate products for a buyer need' and details the catalog-first/live-discovery process. It explicitly distinguishes from siblings: 'find_products is the quick candidate-list tool; research_shopping is the full verified-research job. For a specific brand+model, search_catalog is cheaper...' making purpose and boundaries clear.

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 gives clear when-to-use guidance: 'quick candidate-list tool' and that live web discovery is used 'only when the catalog has no candidates.' It also names alternatives explicitly, such as research_shopping for full research and search_catalog for a specific brand+model, so an agent can choose correctly.

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 description goes far beyond the readOnlyHint annotation, disclosing details about provenance, withholding of stale observations, quote-gated pricing behavior, related_products semantics with direction, and MCP Apps card rendering. This is rich, non-obvious behavior that an agent needs to know for correct invocation and result interpretation.

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 long and dense, but every sentence delivers meaningful information about product data, pricing edge cases, or related_products structure. It is front-loaded with the primary purpose. While it could be structured with bullet points, the wall-of-text format is acceptable given the complexity.

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?

Given the tool's high complexity (provenance, commercial_data, related_products) and the presence of an output schema, the description thoroughly covers all necessary behavioral contexts. It explains edge cases, direction semantics, and client-specific rendering, making it highly complete for an agent.

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 schema already fully documents the slug parameter with an example. The description adds the explicit slug format pattern ('<manufacturer>-<model>') and reiterates the example, which is a slight enhancement. Since schema coverage is 100%, the baseline is 3, and this additional format clarification justifies a 4.

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 clearly states the tool fetches the full golden record and latest price for a single catalog product by slug, with a specific verb ('Get') and precise scope. It distinguishes from sibling tools like compare_products and search_catalog by focusing on a single product's complete record.

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 gives clear in-context usage guidance, such as branching on commercial_data.actionable and handling null prices for quote-gated B2B pricing. It does not explicitly name alternative tools or when-not-to-use scenarios, but the singular slug-based lookup is well implied.

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 include `readOnlyHint: true`, which already indicates a read operation. The description adds valuable behavioral context by specifying exclusion criteria ('Internal/demo and empty catalogs are excluded') and the exact output fields ('name, slug, and product count'). This goes beyond the annotation without contradicting it.

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 sentences: the first states the purpose and filters, the second describes the return value and how to use it. Every sentence is informative, no fluff, and the most important information is front-loaded.

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?

Despite its simplicity, the description fully covers what the tool does, its criteria, and what it returns. An output schema exists, but the description still enumerates the returned fields. Given the zero-parameter nature and clear annotations, the description is complete for an agent to select and use this tool 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?

The tool has zero parameters, so there are no parameter semantics to clarify. The schema is empty and schema description coverage is 100% (there is nothing to cover). The baseline for 0 params is 4, and the description does not need to compensate for any parameter gaps.

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 clearly states the tool's function: 'List public AirShelf merchants that have an assigned slug and at least one active product.' It uses a specific verb ('List') and resource ('merchants'), with clear filtering criteria. This distinguishes it from sibling tools that focus on products, quotes, or searching, so the purpose 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?

The description implies when to use this tool: to obtain a list of eligible merchants, excluding internal/demo and empty catalogs. It also connects usage to a sibling tool by noting the slug is used as the `merchant` argument for `request_quote`. However, it does not explicitly state when not to use it or name alternatives, though the context makes those 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?

Beyond annotations, the description discloses the double opt-in mechanism, the fact that no lead exists or merchant is contacted until confirmation, and the state progression ('confirmation_required', 'awaiting_confirmation', 'received' with reference_number). This is exactly the kind of behavioral context that annotations alone 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?

The description is front-loaded with a one-sentence purpose, followed by a compact flow explanation and a brief edge-case routing rule. Every sentence adds necessary information about behavior or parameter usage; no redundant or generic filler exists.

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 non-trivial two-step quote request with state transitions and merchant-routing nuances, the description covers the confirmation flow, required statuses, and special merchant handling. The high schema coverage and annotations support this, and the description itself explains return-state semantics sufficiently.

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?

With 100% schema coverage, the schema already documents each parameter, but the description adds cross-tool semantics: merchant slugs come from list_merchants, brandSlug is required for airshelf-network routing, and products are catalog slugs. It also explains that the confirmation link goes to contact.email, enriching the contact parameter's meaning.

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?

Description uses a specific verb+object: 'Send a quote request for catalog products to a merchant's sales team on behalf of a named buyer.' This clearly distinguishes the tool from the catalog/research siblings by identifying the quote-request action and the merchant/buyer context.

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 gives clear operational context: it explains the two-step confirmation flow, when a later call is appropriate, and how to choose merchant slugs (including the airshelf-network fallback for network-catalog brands). It does not explicitly name alternative sibling tools for comparison, but the use case is sufficiently distinct.

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?

Reveals asynchronous behavior (returns 'running' + research ID; poll later), refusal statuses for unsafe topics, completion output with per-claim receipts, and market semantics ('available in <market>' is not a stock guarantee). This far exceeds the readOnlyHint/openWorldHint 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?

Seven sentences, each adding a distinct piece of operational guidance; no filler, front-loaded with the definition and sibling contrast.

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?

Output schema exists, so return values are covered; description supplies what schema/annotations lack: async lifecycle, refusal conditions, clarification behavior, and market interpretation, making it fully adequate for a complex 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 covers 100% of parameters with descriptions, so baseline is 3; the description adds valuable context on how `market` biases results and gives an example of the `answers` structure, justifying a 4.

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 clearly it is the 'full verified-research job' for considered purchases, distinctly contrasted with 'find_products' as the quick candidate-list tool, so the agent understands its unique role among siblings.

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 names find_products as the lighter alternative, and documents when it returns 'refused' (unsafe domains) and 'clarification questions' (missing decision details), indicating when to use versus avoid.

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 indicate read-only and open-world behavior, and the description adds substantial behavioral context: `unverified_specs` must not be treated as decisive, tier3 lookup statuses are explained, quote-gated pricing is distinguished from errors, and market availability caveats are detailed. No contradiction with the annotations exists.

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 long but exceptionally well structured with sections, bullet lists, and examples. It front-loads the core purpose and every major block addresses a distinct behavioral or result concern. The length is justified by the tool's complexity, though slightly verbose for a search tool.

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?

The description comprehensively covers query scope, category-specific indexing, result-field semantics, price null handling, tier3 states, market behavior, and failure modes. Given the presence of an output schema and the tool's complexity, this is complete and leaves little ambiguous.

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?

Although the input schema covers all five parameters, the description adds important semantics beyond the schema: the `specs` filter does not apply to certain categories, `market` excludes conflicting country receipts and scopes tier3 lookups, `q` supports budget hints, and the `category` values are enumerated. This is well above the 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 opens with a specific verb and resource: 'Search the AirShelf cross-vendor product catalog by natural-language query.' It further distinguishes the tool by enumerating the catalog categories it covers, which makes its scope clear relative to sibling product 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?

The description provides clear context for when to use the tool via example queries and category-specific guidance (e.g., 'Industrial-automation and wiring-device rows are indexed by manufacturer part number... the `specs` filter does not apply to them'). It stops short of explicitly naming alternative tools or when-not-to-use conditions, so it misses the top score.

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