Oxbox Energy 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 readOnlyHint, idempotentHint, destructiveHint=false and closed-world scope, so the safety profile is covered. The description adds genuinely new behavioral context by stating what comes back ('each series with its product page and documents'), which matters because there is no output schema; it does not mention pagination or empty-result 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, zero filler: the first front-loads the searchable dimensions, the second states the return contents. Every clause carries information an agent needs to construct a call.

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 5-parameter, all-optional lookup with no output schema and full schema coverage, the description covers what can be filtered and what comes back. It stops short of explaining filter combination semantics or result-size limits, which is a minor but real gap for a discovery 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 description coverage is 100%, so all five parameters are already documented with examples, and the description largely repeats those same value lists (VRLA gel, AGM, 2 V, 6 V, telecom, UPS). It adds no information about how multiple filters combine or whether the optional 'text' and 'include_discontinued' params interact with the others, 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 a specific verb and resource ('Find a stationary battery or product series that Oxbox Energy offers') and enumerates the three filter dimensions plus the return contents. It does not differentiate itself from the sibling tool 'search', so the agent cannot tell from the description alone which one to pick when looking for a product.

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 enumerated filter axes: use this when you know a chemistry, voltage or application. There is no explicit when-not guidance and no routing to alternatives such as 'search', 'fetch' or 'sizing_tool', leaving the agent to infer the boundary with the generic search sibling.

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 the tool as read-only, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds one useful behavioral detail—third-party documents are linked at their source—but does not describe result ordering, pagination, or what the document records contain.

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 definition is a single front-loaded sentence that begins with the action and resource, then gives scope and document types. The long type list is somewhat repetitive of the enum but still useful for quick comprehension, and 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 two-parameter list tool with no output schema, the description covers the main scoping modes and notes that third-party docs link out. It is still missing practical details such as what fields each returned document includes and whether results are paginated or ordered.

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 50%: the series parameter is documented as accepting a find_series id or name, while type is an enum. The description reinforces the type values and the 'across the site' behavior, but it omits the 'other' enum value and does not clarify that both parameters are optional or how they combine.

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 ('List the documents Oxbox Energy publishes') and explains the two supported scopes: by series or by document type across the site. It distinguishes the tool's content from generic series lookup, but it does not explicitly name or differentiate it from siblings like search or fetch.

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 usage through its two filtering modes ('for a series, or of one type across the site'), which helps an agent understand how to call it. However, it gives no explicit guidance on when to use this instead of search, fetch, or find_series, and it does not state exclusions or prerequisites.

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, idempotentHint, and destructiveHint=false. The description reinforces this by explicitly stating the tool performs no action and the customer sends the request themselves, which is a meaningful behavioral claim beyond the annotations for a tool whose name suggests submission.

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 compact sentences that lead with what is returned and end with the crucial non-action clarification. Only the "round of questions" clause is mildly decorative, but it earns its place by motivating the parameters.

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, no-parameter-required informational tool with full schema coverage and clear annotations, this covers what an agent needs: what it returns and that it has no side effects. Only the lack of sibling routing keeps it from a 5.

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 both parameters are optional with their own descriptions, so the schema carries the detail. The description's phrase "what to include so the engineers can answer without a round of questions" hints at why series and application matter but adds no format or usage detail 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 states what the tool actually returns: the address to write to and the information to include when requesting a quote from Oxbox Energy. It usefully corrects the misleading name by clarifying that no request is sent, though it does not distinguish itself from siblings such as sizing_tool or get_documents.

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 sends nothing; the customer sends the request themselves" implicitly rules out expecting a submitted quote, which is useful negative guidance. However, it never names an alternative tool or states when an agent should prefer sizing_tool or find_series first.

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 closed-world behavior, so safety is covered. The description adds valuable context the annotations cannot: what the tool returns (ids, titles, source links) and that results are references to be resolved with fetch rather than full documents.

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 first front-loads scope and content types, the second gives query guidance and the return/resolution contract. 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 one-parameter search with no output schema, the description covers scope, query style, return fields and the next step. Minor gaps remain: no mention of result limits or ranking behavior, and no explicit contrast with the other content-oriented siblings.

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 the single parameter is documented, but the schema text ("What to look for.") is minimal. The description compensates by specifying that queries should be plain natural language and supplying two concrete query shapes, which meaningfully guides how to populate the parameter.

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 verb (search) and resource domain (the Oxbox Energy website) and enumerates the exact content covered: product pages, datasheets, discharge tables, manuals, SDS and technical articles. An agent can distinguish it immediately from fetch (single-document read) and from the more targeted 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?

It gives concrete usage context via natural-language examples ("12 V gel battery for solar", "OPzS 2V cell SDS") and explicitly routes the follow-up step to fetch. It does not explain when to prefer find_series or get_documents over a free-text search, so the sibling differentiation is only partial.

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 the crucial behavioral fact that the connector has no sizing capability, preventing an agent from misusing it as a calculator; it adds little else about the response shape, which is fine for a text-only guidance tool.

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 the critical negation front-loaded so an agent cannot miss it. There is minor redundancy between 'NO online sizing tool' and 'cannot size a system', but each targets a different actor (vendor vs connector), so it mostly 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?

For a zero-parameter, no-output-schema informational tool, the description supplies everything an agent needs: what it is not, what it is, and the concrete inputs a customer must provide. Nothing required to call or interpret it 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?

Zero parameters, so the baseline is 4; there is nothing for the schema to document. The description uses the space well by naming the data the customer must supply (load, runtime, voltage), which is the only 'input' concept relevant to this tool.

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 this is an informational tool: it does NOT size a system and instead explains the manual path to getting one sized. That distinguishes it from siblings like quote_request, though it does so by describing a process rather than naming the sibling tool directly.

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 sets a clear expectation of when to use it (when a customer needs sizing guidance) and explicitly rules out what it cannot do (size a system). It points at the quote-request path with the required inputs, but never names the quote_request sibling, so the handoff is implied rather than explicit.

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