Enervia Power — Solar & BESS sizing

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the agent knows this is a safe, self-contained computation. The description adds the useful fact that this is a pure calculation whose result is the three named quantities, which partially compensates for the absent output schema, but it discloses nothing about units, assumptions, or failure behavior beyond that.

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 bilingual sentences, front-loaded with the purpose and immediately followed by the same statement in English. Nothing is wasted and no sentence is 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 10-parameter calculator with full schema coverage and no output schema, the description supplies the essential missing piece — what the calculation returns. It stops short of clarifying the mode-dependent parameter split and the template-vs-appliances relationship, but the schema covers those.

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 each parameter (mode, panelW, sunHours, template, appliances, backupHours, autonomyDays, concurrencyPct) already carries a Persian explanation, including mode-specific applicability. The description adds no parameter-level meaning beyond the schema, 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?

The description names a specific verb (calculate) and enumerates the concrete outputs — battery capacity, inverter power, solar panel count — and scopes them to backup or off-grid systems. It is far clearer than a tautology, but it does not differentiate itself from the related sibling list_load_templates, which supplies the preset templates the 'template' parameter consumes.

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 states the domain context ('backup or off-grid') and that input can come from a load list or peak load, which implies usage. However, it never says when to choose this tool over list_load_templates, nor that templates should be fetched first, and gives no 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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safe-read profile is covered. The description adds what content is returned (addresses, hours, warranty URLs), which is useful, but says nothing about whether the data is static or refreshed, or how it is formatted. With annotations carrying the safety burden, a 3 fits.

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 content is front-loaded and short, but the same list is stated twice, once in Persian and once in English, which doubles the length for a single-resource tool. That mirroring does not add information an agent needs beyond reading one language.

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 parameters and no output schema, the description carries the burden of enumerating what is returned, and it does so reasonably well (addresses, phones, hours, service/warranty URLs). It stops short of describing structure or completeness of that data, but nothing essential for invoking a zero-argument info tool 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?

The tool takes zero parameters, so the baseline of 4 applies; there is no parameter semantics for the description to compensate for. No syntax or filtering details are needed.

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 concrete resource (EnerviaPower addresses, phone numbers, opening hours, service-request/warranty URLs), so the agent knows exactly what data comes back. It is implicitly distinct from all siblings (calculate_bess_system, list_products, search_articles), though it never states a verb or explicitly differentiates itself.

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: an agent can infer this is for contact/service-request questions, but there is no explicit when-to-use statement and no alternative tool offered, because none of the siblings overlap in purpose. Adequate but with an obvious gap.

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 readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the templates are built-in/fixed (not user-created) and the listing includes associated devices. It does not cover pagination or ordering, but for a static template list that is minor.

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 resource and category examples. The Persian and English sentences are near-duplicates, a mild redundancy, but each remains compact and the bilingual pattern is presumably intentional.

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 parameterless read-only listing with no output schema, the description supplies what the agent needs: what the profiles are, representative categories, and that device data comes back with them. Nothing material is left unstated for a tool of this complexity.

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 there is nothing to disambiguate and the schema requires no compensation. Baseline 4 applies; no parameter-related information is missing.

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?

Clear specific verb+resource: 'list the built-in load profiles the calculator can start from,' with concrete examples (apartment, villa, office, store). This distinguishes it from calculate_bess_system, which consumes those profiles. It does not explicitly name sibling alternatives, but the resource 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 calculator can start from' hints that this is a discovery step preceding calculate_bess_system, which is useful implied usage. However there is no explicit when-to-use statement, no when-not, and no named alternative to route to.

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 openWorldHint=false, so safety and scope are covered by structured fields. The description adds the catalog's content scope (storage, inverters, portable) but says nothing about return shape, pagination, or whether the list is static or live — modest added value on top of 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, but they are bilingual duplicates that convey identical information, so roughly half the text is redundant rather than additive. It is still front-loaded and easy to parse, but not maximally economical.

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 listing with no output schema, the description covers what the catalog contains but not what a caller receives (item fields, pagination, empty-result behavior). Adequate for routing, thin on what to expect from 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?

The tool takes zero parameters, so the baseline is 4 and there is no parameter semantics to document. Nothing in the description contradicts or misleads about the no-argument call signature.

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 English sentence gives a clear verb (Return) plus resource (EnerviaPower product catalog) and enumerates what the catalog contains (storage, inverters, portable), which is more than a restatement of the name. It does not, however, distinguish itself from the sibling tool suggest_products, which an agent could easily confuse with a plain catalog listing.

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 guidance is given about when to call this versus suggest_products or list_load_templates, nor any prerequisite or context. The description only says what is returned, leaving the agent to infer that this is the exhaustive catalog read and suggest_products is the recommendation path.

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 readOnlyHint=true and openWorldHint=false, and the description adds genuinely useful behavior: the exact fields returned (title, URL, excerpt, date) and the empty-query fallback to newest articles. It does not cover pagination or result-count 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?

Front-loads the purpose, then return fields, then the empty-query rule; every sentence carries information. The Persian and English statements are near-duplicates, which adds length but serves the bilingual audience.

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 return fields, and both parameters are documented. It is largely self-sufficient for a two-parameter read tool, missing only minor details like result ordering or pagination.

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 baseline is 3, but the description adds real semantics for the optional `query` parameter by disclosing that an empty value returns the newest articles. The `limit` parameter is left entirely to 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 gives a specific verb (search) and resource (EnerviaPower knowledge base articles) and scopes the domain to Persian solar/battery/power content. It is clearly distinct from the sibling tools (products, contact, calculators), though it never names or contrasts them 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?

Usage context is clear: it queries the article knowledge base, and the empty-query-browses-newest behavior tells the agent a valid calling pattern beyond a keyword search. There are no explicit exclusions or named alternatives, so it falls 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?

Annotations already declare readOnlyHint=true and openWorldHint=false, which matches a read-only recommendation against a fixed catalog. The description adds the notable behavioral fact that the input contract mirrors calculate_bess_system, but says nothing about what is returned (pricing, quantities, panel/battery counts) or whether the calculation must be run first. 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?

Two sentences, front-loaded with the purpose, and the cross-reference to the sibling is placed last where it belongs. Slight redundancy from stating essentially the same content in Persian and then English, but it is compact overall.

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 10-parameter tool with no output schema, the agent gets no information about the shape of the recommendation (unit counts, model names, pricing) or whether calculate_bess_system must be invoked first. The annotation covers the safety profile, but the output/interaction model with the sibling calculation tool remains underspecified.

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% with rich Persian descriptions for all 10 parameters, so the schema does the heavy lifting. The description adds one useful cross-reference (same inputs as calculate_bess_system) but no additional parameter meaning beyond the schema. Baseline 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?

States a specific verb (suggest) and resource (EnerviaPower products), and enumerates the categories returned: inverter, battery, panel. It also anchors the tool to the calculated system size. It does not explicitly distinguish itself from the sibling list_products, which an agent could easily confuse with a recommendation tool.

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?

"Based on calculated need" and "accepts the same inputs as calculate_bess_system" imply this is used after (or alongside) that calculation, which is useful implied guidance. However there is no explicit when-to-use/when-not-to-use statement and no stated relationship to list_products, so the agent must infer the workflow.

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