BAE Batteries USA product catalogue

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so safety is covered. The description goes beyond that by disclosing conditional return behavior: a discharge table yields figures only after datasheet verification, otherwise just the link and page. That is real behavioral context the annotations cannot express, though the condition itself is phrased vaguely.

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, front-loaded with the core purpose. The second sentence about discharge tables is somewhat cryptic but does not pad the description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description must carry the return-value burden, and it does so only partially: it hints at 'link and page' versus figures for discharge tables, but never clarifies what 'full text' means for a product series or how the non-discharge case is shaped. Adequate but leaves an agent guessing at the response.

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 a single parameter with 100% schema description coverage, so the schema already explains that id comes from search, find_series or get_documents. The description adds only the notion that exactly one result is read, which is a marginal restatement rather than new semantics.

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: 'Read the full text of one result from search', and enumerates the item types it covers (web page, PDF, product series). It clearly separates itself from search by being single-result retrieval, though it doesn't explicitly contrast with get_documents or find_series, which also produce ids.

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 'one result from search' — fetch comes after search. There is no explicit statement of when to prefer this tool over get_documents, find_series, or search, 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 read-only, idempotent, non-destructive and closed-world behavior, so the description only needs to add context. It does add that results include each series' product page and documents, which is useful since there is no output schema. Pagination and behavior on empty results are unstated.

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, zero filler: the capability and its filter facets come first, and the return content follows. Nothing is buried or repeated.

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 an all-optional 5-parameter search tool with no output schema, the description covers what can be filtered and roughly what is returned. It leaves open how multiple filters combine (AND vs OR), whether result sets are capped, and how discontinued series behave beyond the schema's default note.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so all five parameters are already documented. The description restates the same chemistry/voltage/application values (with '...' hinting at more) but adds no syntax, matching behavior, or combination logic 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?

Uses a specific verb ('Find') and a precise resource ('stationary battery or product series that BAE Batteries USA offers'), and enumerates the filter facets. It does not name or differentiate itself from sibling tools like search or fetch, 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?

The enumeration of chemistry/voltage/application implies when this lookup is appropriate, but there is no explicit guidance on when to use it versus the generic 'search' tool or when to switch to 'fetch'. 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 declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds a useful behavioral note that third-party documents are linked at their source, but it says nothing about return format, volume, or pagination, so the added value is modest.

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?

It is a single front-loaded sentence that states the action and scope first, then enumerates types, and ends with the third-party linking note. Every clause carries information; there is no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter read tool with strong annotations and no output schema, the description covers scope and document types adequately. It could mention whether results are paginated or how many documents are returned, but nothing essential is missing for correct invocation.

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 50%: the 'series' parameter is documented in the schema, while 'type' has only an enum. The description repeats the enum values rather than explaining them further, but it does clarify that type alone can be used to list across the site. That is a partial compensation, consistent with a 3.

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 ('List') and resource ('documents BAE Batteries USA publishes'), with scope: for a series or by type across the site. It enumerates document types concretely, which makes the tool's purpose unambiguous. It does not explicitly contrast itself with siblings like search or fetch, 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?

It conveys the two usage modes ('for a series, or of one type across the site'), which implies when this tool is appropriate. However, it gives no explicit when-not-to-use guidance and does not name an alternative sibling such as search when a broad keyword lookup is needed.

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 readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds useful behavioral context by stating 'It sends nothing; the customer sends the request themselves,' which prevents the agent from treating this as an outbound message-sending action. It does not describe return formatting or pagination, but that is minor here.

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 tight sentences with no wasted text. It front-loads the core purpose and immediately clarifies the non-sending behavior, which is the most important nuance for an agent to understand.

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 guidance tool with fully documented optional parameters, rich annotations, and no output schema, the description is complete enough. It states what the tool provides: the address and what to include so engineers can answer without back-and-forth.

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 optional parameters already have clear descriptions in the schema. The description does not add specific meaning about how series or application affect the guidance, so the baseline score of 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 clearly states the tool's purpose: it provides the address and the information to include when asking BAE Batteries USA for a quote or price. It is specific about the resource and even clarifies that the tool sends nothing, but it does not explicitly differentiate itself from siblings such as sizing_tool or find_series.

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: an agent should use this when a customer needs quote or pricing contact instructions rather than product data. However, there is no explicit when-to-use guidance, no exclusions, and no named alternatives among the sibling 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, idempotentHint and openWorldHint=false, so the safety profile is covered. The description still adds value by disclosing the return shape (ids, titles, source links) and the two-step search-then-fetch pattern, which annotations cannot convey. It stops short of noting result limits or ranking behavior, so not a 5.

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 corpus scope, then examples, then the return-and-follow-up instruction. Every clause carries information an agent would otherwise have to guess at; nothing is redundant with the title 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?

No output schema exists, but the description compensates by naming the returned fields (ids, titles, source links) and explaining how to turn a hit into full content via fetch. Combined with full parameter coverage and read-only annotations, an agent has everything needed to invoke this correctly on the first try.

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?

Only one parameter and schema coverage is 100%, so the baseline is 3. The description earns above that by demonstrating the intended query form with two worked examples ("12 V gel battery for solar", "OPzS 2V cell SDS"), which tells the agent how to phrase input in a way the terse schema description "What to look for." 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?

States a specific verb (Search) plus the exact resource and enumerates the content corpus: product pages, datasheets, discharge tables, manuals, SDS, technical articles. This is far more specific than the title and lets an agent distinguish it from get_documents or find_series, which target narrower slices of the same site.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit query-style guidance ("Ask in plain words") with two concrete example queries, and routes the agent onward: "Returns ids, titles and source links; read one with fetch." That names the sibling fetch and the condition for using it, which is exactly the when-to-use signal an agent needs.

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 readOnly/idempotent/non-destructive, and the description adds genuinely new behavioral information: the connector does not perform sizing, the user must run the tool, and results are provisional until engineering confirms. It does not specify the exact return shape (bare URL string vs. an object with a location), which is the only gap.

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, with the core purpose front-loaded, so the agent can decide quickly. The clause 'and where the website links it' is vague and mildly wasteful, but nothing else is padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter, read-only link tool with no output schema, the description covers what it is, who runs it, and how much to trust the result. Only the literal return format is left unspecified, a minor gap at this complexity level.

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 zero parameters, so the baseline is 4; there is nothing for the description to disambiguate. The description correctly implies no inputs are 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?

The description makes clear that this tool returns a link to an external battery-sizing web tool rather than computing a size, which separates it from siblings like get_documents or quote_request. The phrasing 'the online tool ... and where the website links it' is a bit roundabout about exactly what is returned, and no sibling is named explicitly, 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?

'The customer runs it themselves; this connector cannot' and 'A starting point only: engineers confirm every size before it is quoted' give clear context for when this is the right call and set expectations that it is not an authoritative answer. It does not explicitly route the agent elsewhere (e.g., to quote_request for an actual quote), which keeps it at 4.

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