Reliance Trenchless Catalogue

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

With readOnlyHint/openWorldHint/destructiveHint already covering the safety profile, the description adds real behavioral context: the input must be *published* products (an eligibility constraint absent from the schema) and the tool's output surfaces dimensions or operating details still requiring confirmation, i.e. it is a gap-finder rather than a plain differential. It stops short of describing ordering, failure modes, or result 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?

A single, front-loaded sentence with no filler; the verb-resource-arity information comes first. The trailing clause about 'dimensions or operating details' is slightly vague but still earns its place by signalling the output intent.

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 one-parameter, read-only comparison tool with no nested objects, the description is close to sufficient, and it partly compensates for the missing output schema by hinting at what the comparison returns. It leaves the exact comparison dimensions and result format unstated, which is the only 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?

There is one parameter at 100% schema description coverage, and the schema already encodes minItems=2/maxItems=4 plus the accepted identifier forms. The description only restates the cardinality ('two to four'), adding no syntax or semantics beyond the structured fields, 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?

States a specific verb (Compare) and resource (products) with an explicit arity of 'two to four published products', which an agent can act on directly. It does not, however, name or differentiate itself from the closest siblings (get_product, shortlist_products), so the boundary 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?

Usage is only implied: the 'two to four published products' scope and the 'still need confirmation' phrasing hint at a gap-analysis use case, but there is no explicit when-to-use, when-not, or routing to siblings such as shortlist_products or get_product.

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 this a safe, read-only, closed-world operation, so the safety profile is covered. The description adds useful disclosure of what content comes back (overview, technical guide, source notes, spec tables, documents), but says nothing about behavior on an unknown product, pagination, or document access constraints.

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 verb and the returned content are stated immediately and every clause 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?

With no output schema, the description usefully enumerates the returned sections, so an agent knows what it gets. Missing only error/not-found behavior and routing guidance versus siblings, which are minor for a low-risk read tool with annotations covering safety.

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?

One parameter with 100% schema description coverage, so the schema fully documents that name, ID, or canonical URL slug are accepted. The description adds nothing about the identifier beyond 'one product', which is the expected baseline when the schema does the 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?

States a specific verb (return) plus resource (the published overview, technical guide, source notes, spec tables, documents for one product). The phrase 'for one product' implicitly contrasts with the multi-product sibling compare_products, but no sibling is named, so differentiation is only implied.

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: the singular 'one product' suggests fetching full detail for a single known product rather than searching or comparing. There is no explicit when-to-use statement, no conditions, and no named alternative such as search_products or compare_products.

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 one useful behavioral fact — only 'published' families are returned — and indicates canonical pages are attached, but says nothing about ordering, count, or pagination.

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. Every clause ('published', 'canonical pages') carries information.

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 no-parameter list tool with no output schema, the description adequately conveys what is returned (families plus their canonical pages). It could say more about result shape or size, but annotations cover the safety profile and there is little else an agent needs.

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?

Zero parameters, so per the rubric the baseline is 4. Nothing in the schema needs clarifying and the description correctly implies no filtering input is required.

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') and resource ('product families'), plus a scope qualifier ('published') and what comes back ('canonical pages'). This is clearly distinct from the sibling get_product or search_products, though the description never names those alternatives 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?

No when-to-use guidance, no exclusions, and no mention of the sibling tools an agent might confuse it with (search_products, get_product, shortlist_products). The enumerating role is only implied by the verb 'List'.

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, openWorldHint=false, and destructiveHint=false, and the sentence 'does not send email or place an order' is consistent with and mildly reinforces that safety profile. However, it adds nothing about what the generated checklist contains, whether state is persisted, or any permission requirements, so beyond annotation restatement the value is limited.

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, front-loaded sentences with no filler; the exclusion is placed right after the purpose. It is arguably under-specified rather than over-long, so the sizing itself is efficient.

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 12-parameter tool with no required fields, no output schema, and zero schema documentation, the description leaves the agent without enough information to populate the inputs meaningfully or anticipate the output. It covers purpose and one negative behavior only.

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 takes 12 parameters with 0% schema description coverage, and the description offers only the vague phrase 'known project facts' rather than explaining what any field means (e.g. task vs defectOrIntendedTask, units for pipeDiameterMm). With low coverage the description is expected to compensate, and it does not.

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 transformation (project facts -> review checklist for Reliance), which is a specific verb+resource, and the tool is clearly distinct from the product-catalog siblings. It stops short of a 5 because 'prepare' is abstract and the nature of the checklist is not described.

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 gives negative guidance ('does not send email or place an order') but never says when to reach for this tool versus the sibling product tools or what preconditions make it appropriate. No alternatives or triggers are named.

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 covered. The description adds one real behavioral constraint beyond that — it only returns 'published' products, excluding drafts/unpublished items. It says nothing about result caps, ranking, or 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?

A single front-loaded sentence with no filler. The verb, resource, and search axes all appear immediately, and nothing is repeated from the schema or annotations.

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 three-parameter search tool with no output schema, the definition is adequate but thin: it never says what a result contains (product IDs, names, snippets), how results are ranked or limited, or how it relates to shortlist_products/compare_products downstream. Annotations carry the safety profile, but the search-then-narrow workflow is left to inference.

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 67%, so baseline is 3. The description's listing of searchable dimensions (task, product name, pipe application, family) does add semantic framing for what the required `query` matches against, but it supplies nothing for `maxResults`, which is undocumented in both the schema and the 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 states a specific verb (Find) and resource (published Reliance products) and enumerates the searchable dimensions (task, product name, pipe application, product family). It is clearly distinguishable from get_product (single retrieval) and list_product_families, but it does not differentiate itself from shortlist_products, which sounds like an adjacent search/curation operation.

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 word 'Find' but there is no explicit when-to-use guidance, no exclusions, and no routing to siblings like shortlist_products or compare_products. The one useful cue is the reference to list_product_families as the source for the family slug, which implies a natural call ordering.

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 of the call is covered. The description adds real value beyond that by disclosing the return semantics (candidates plus missing information) and explicitly disclaiming that results constitute approval of a model or procedure — a meaningful boundary in an engineering domain.

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, no filler, and the core purpose is front-loaded before the output/limitation note. Every clause carries information.

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 helpfully sketches what comes back and what it does not guarantee. But for a 5-parameter tool with 40% schema coverage and three untyped/undescribed inputs, an agent lacks guidance on how pipeMaterial, bypassRequired, and serviceConditions affect results.

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 only 40%: pipeMaterial, bypassRequired, and serviceConditions have no schema descriptions at all. The description says nothing about these inputs, so it fails to compensate for the coverage gap; only the 'task' concept is echoed.

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: mapping a stated task to Reliance product families. The second sentence clarifies output (enquiry candidates and missing information), which distinguishes it from a pure lookup like get_product or a comparison tool. It stops short of explicitly naming which sibling to use instead, so not 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 negative boundary ('does not approve a model or operating procedure') usefully tells the agent this is a pre-enquiry step, implicitly upstream of prepare_technical_enquiry. However, it never states when to choose this over search_products or compare_products, leaving the alternative selection to inference.

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