Modulit Pro AV Finder

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 profile is covered. The description adds a genuine behavioral caveat beyond annotations — that the output is a length figure, not a signal-reach guarantee. It says nothing about rounding, units of the result, allowed edge cases, or why two storefronts exist.

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, front-loaded with the action and immediately followed by input semantics and the output caveat. No filler; the only mild vagueness is the word 'sections', which is not a schema term.

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 11-parameter, annotation-light, no-output-schema tool the description is partially adequate: it names the return value and the general input families. It is not complete enough to call confidently, since required 'storefront', the large 'signal' enum, and 'quantity' are unexplained and nothing describes result precision or units.

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 0% across 11 parameters, so the description must carry the burden. It loosely groups parameters into semantic buckets ('sections in metres, loops, installation route and allowance') that map to horizontal/drop/rise/travel, loopFrom/loopTo, routing and wastePercent, which is real added value. However, it never explains storefront (required, enum eu/pl), the 24-value signal enum, quantity, or which of 'sections' means horizontal vs drop vs rise.

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 purpose: run the native Modulit cable calculator and return required cable length from sections in metres, loops, routing and allowance. It also clarifies the output is a length estimate, not a signal-integrity certification. Sibling tools (product search, power config) are unrelated, so explicit differentiation is unnecessary, but the verb is implied rather than stated as 'calculate cable length'.

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 implicitly defines the use case (estimating cable runs) and gives one useful scope exclusion: the result is not a certification of signal reach. There is no statement of when to prefer this over manual estimation or other tools, no mention of required prerequisites, and no guidance on storefront selection despite 'storefront' being required.

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 the mode behavior that omitting state lists choices, but it does not disclose return format, permissions, or other operational details. There is 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 two sentences, front-loaded with the two main modes, and contains no redundant wording. Every sentence contributes to understanding the tool's purpose and the state-omission behavior.

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 tool has a nested state object with nine cryptic fields, a required storefront parameter, and no output schema. The description explains the two modes but does not explain the return shape or map the state fields, leaving significant gaps 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 description coverage is 0%, and the nested state object uses cryptic keys such as hc, pre, s, cvr, mnt, rc, enc, and gst. The description names several domain concepts like housing, preset, socket, covers, mount, and quantity, but it does not map them to the parameter keys or explain storefront, rc, enc, or gst.

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 specific verbs and resources: inspect native PureLink mediahub2 choices or resolve a housing, preset, socket, covers, mount and quantity into a bill of materials. It clearly distinguishes two operating modes, though it does not explicitly differentiate itself from sibling tools such as configure_power or describe_power_selector.

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 explicitly says to omit state to list choices, which implies that providing state resolves a bill of materials. However, it gives no guidance on when to use this tool versus siblings, no prerequisites, and no exclusions.

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, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The only behavioral claim the description adds, "Missing evidence is counted separately," is unexplained jargon that gives no actionable insight into what the tool computes or returns. With no output schema, a reader learns nothing about the result shape beyond a vague hint that gaps are tallied.

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 with no padding, which is appropriately sized. However, the second sentence is cryptic filler rather than front-loaded useful detail, so brevity comes at the cost of substance rather than from efficiency.

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?

A four-parameter tool with required nested free-form input, an enum, and no output schema demands substantial explanatory text, and this provides none. An agent cannot determine what to put in "values" or what a call will produce. The definition is not adequate for the tool's 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?

Schema description coverage is 0% across four parameters, including a free-form nested "values" object whose allowable keys and meaning are completely undocumented. The description only obliquely references "storefront" and says nothing about "values", "limit", "offset", or the eu/pl enum. This is exactly the case where the description must compensate for the schema 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 says it will "Run the native SurgeX equipment selector for this storefront," which conveys a rough domain (power/equipment selection for a given storefront) but uses a vague verb ("run") and never states what the tool actually produces or configures. The name configure_power suggests configuration, while the description suggests an evaluation/selector invocation, leaving the actual purpose ambiguous. The sibling describe_power_selector is not distinguished from it at all.

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?

There is no guidance on when to call this versus the closely related siblings describe_power_selector, get_products, or configure_mediahub. No preconditions, no exclusions, and no statement of what a caller must have prepared before invoking it. Usage must be entirely inferred from the tool name.

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, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered externally. The description contributes by indicating the payload contains field names plus their allowed values, but it says nothing about size limits, ordering, caching, or whether the vocabulary is stable across firmware versions.

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 short sentence with no filler, and the key concept (fields plus allowed values) is up front. Nothing can be trimmed without losing 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 carries the burden of explaining returns, and it does so only at a high level: 'selector fields and allowed values.' That is enough to know roughly what comes back, but not the shape (field names, enums, defaults) an agent would need to use the result in a follow-up call.

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 there is no parameter meaning to convey and the schema is trivially complete. Baseline 4 applies; nothing in the description is needed to clarify inputs.

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 concrete verb and resource: 'Get the native SurgeX selector fields and allowed values,' which tells an agent this is a schema/introspection lookup rather than a mutation. It is clear on its own, but it never distinguishes itself from siblings such as configure_power or get_products, which arguably overlap in domain.

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?

There is no explicit when-to-use statement and no mention of alternatives or prerequisites. An agent can loosely infer that this should be called before configure_power to learn valid selector fields, but that inference is nowhere stated in the description.

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 the safety profile is fully covered elsewhere. The description adds one genuinely new behavioral fact — availability is only returned 'when displayed by this storefront' — but says nothing about partial matches, missing products, or error behavior for a batch lookup.

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 constraint and the return contract come before any elaboration. It is compact and readable, though the batching limit overlaps with structured schema data.

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 read-only lookup with no output schema, the description does state the shape of the result, which is important. It stops short on the language parameter's effect on returned values and on how missing or non-displayed products surface in 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?

Schema description coverage is 0%, so the description must carry the load. It explains the products array as 1–20 exact IDs or SKUs and gives 'this storefront' meaning to the storefront parameter, but the language parameter (12-value enum) is completely unmentioned and the 20-item cap merely restates maxItems already in 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?

States a specific verb and resource ('Look up ... exact product IDs or SKUs') and pins the scope with 'exact', which distinguishes it from the sibling search_products without naming it. The return payload (public MSRP, indicative availability) is also named, making the tool's identity 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 word 'exact' implies this is the tool for known identifiers rather than discovery, which is usable guidance. However, it never states when to prefer search_products instead, nor what happens when an ID is unknown or unavailable in the given storefront — usage is implied rather than spelled out.

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 that this is a read-only, idempotent, non-destructive, closed-world operation. The description adds meaningful behavior beyond that: missing evidence is treated as non-matching, and installation-specific compatibility is explicitly outside the match result and must still be checked.

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 short and front-loaded: the comparison purpose comes first, followed by two concise caveats. Every sentence carries domain meaning and there is no redundant wording.

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 seven-parameter nested search tool with no output schema and no schema descriptions, the definition is too thin. It supplies useful match caveats, but it omits parameter semantics, return behavior, and sibling-tool selection guidance.

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 seven parameters, nested objects, and 0% schema description coverage, the description should carry parameter meaning but does not. It vaguely references source technical requirements, but it does not explain the source id/sku forms, technical filters, sort, pagination, storefront, or language parameters.

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 comparison action against source technical requirements, so the core purpose is clear enough to act on. However, it does not clarify whether the tool searches/returns candidate products or performs a direct comparison, and it gives no distinction from sibling search_products.

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 no explicit guidance on when to use this tool versus alternatives such as search_products or get_products. The caveats about missing evidence and installation compatibility are domain rules, not usage-selection guidance.

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 read-only, idempotent, closed-world operation, so the safety profile is covered. The description adds non-obvious behavior the annotations cannot: results are policy-scoped by storefront, some prices are hidden and therefore unsortable, and technical constraints are treated as mandatory rather than soft signals. It doesn't describe pagination limits or result shape, which keeps it below 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?

Three dense sentences, front-loaded with the searchable facets, then ordering policy, then sort restrictions — no filler. The phrase 'inherits public storefront brand/lifecycle policy' is compact to the point of being cryptic for an agent unfamiliar with the underlying policy model.

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 7-parameter tool with nested filter objects and no output schema, the description covers intent, ordering and one hard constraint but leaves result pagination (limit/offset bounds) and language behavior unexplained. It is adequate to start a call but not complete enough for an agent to fully predict retrieval behavior.

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 0%, so the description carries the burden, and it does explain the intent of q (SKU, free text, engineering requirements), sort (msrp-only, in the stated currency) and implicitly the technical filter object. However, limit, offset, language and the availability/maxMsrp filters go unmentioned, leaving several parameters with no semantic guidance anywhere.

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 ('Find products by SKU, product text, engineering requirements or visible MSRP/status'), which tells an agent exactly what surface area is searchable. It implicitly separates itself from get_products (lookup) and search_product_analogs, but never names a sibling, so differentiation 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?

It gives real when/when-not guidance: sort is only for an explicit price order, hidden prices cannot be sorted, and default ordering follows storefront brand/lifecycle policy. It stops short of naming alternatives such as get_products or search_product_analogs and doesn't say when a direct lookup should replace a search.

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 the safety profile is covered. The description adds a genuinely useful epistemic caveat — that catalogue links signal published pages only and compatibility rests on structured facts — but says nothing about how results are ordered, paginated, or what a result entry contains.

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, front-loaded sentences with no filler; the purpose comes first and the alternative routing last. The middle clause is compressed to the point of jargon ('only structured facts support compatibility') but it is load-bearing rather than 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 seven-parameter tool with nested filter objects, no output schema and zero schema-level parameter descriptions, three sentences are not enough — an agent cannot tell what sort/filters/currency semantics mean or what a returned hit looks like. Only the read-only safety profile is adequately covered, and that comes from annotations rather than the text.

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 0% across seven parameters, including nested objects for sort and filters (maxMsrp, technical.brand/videoMode/minLengthM/maxLengthM/application, availability), yet the description only hint at the query field via 'task, model or SKU'. Nothing explains the numeric conventions (amountMinor), currency pairing, or what the technical filters constrain, so the description fails to compensate for the absent schema documentation.

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 concrete verb and a set of resources: 'Find published solutions, guides, tools and products' with the search surface named ('for a task, model or SKU'). It explicitly separates itself from get_products, but gives no cue to distinguish it from the sibling search_products or search_product_analogs, which an agent would also plausibly pick for a query.

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?

There is one explicit routing rule ('Use get_products for current terms') and an implicit signal that this tool is for published content rather than live pricing. However, the agent is told nothing about when to prefer search_products or search_product_analogs over this tool, which is the main selection risk given the sibling list.

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