catalog

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

No annotations are provided, so the description carries the full burden. It usefully discloses two behavioral traits: the answer comes solely from catalog fitment data, and the result is 'unknown' when no fitment data exists. However, it says nothing about permissions, latency, or whether sku/product_id are alternative identifiers, so significant burden remains unaddressed.

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 question, followed immediately by the data-source and unknown-result caveats. 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 read query with no output schema this is nearly adequate: it explains the answer semantics (fit / unknown). But with no annotations and only 33% schema coverage, the missing guidance on the two undocumented identifiers leaves the definition incomplete 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 only 33%: antenna_model is documented ('Model slug or common name') but sku and product_id are not. The description says nothing about parameters, so it fails to clarify whether sku and product_id are alternate ways to identify the same part or whether both must be supplied. It does not compensate for the coverage gap.

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 question the tool answers ('Does a part fit a given antenna model?'), which is a clear verb+resource even though it is phrased interrogatively. It is readily distinguishable from siblings like get_quote, resolve_supersession, and search_parts. It stops short of explicitly naming those alternatives.

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: this is the tool to call when you need a fitment answer. The clause 'Answers from the catalog fitment data only' scopes the source but does not say when to prefer this over search_parts or how to handle parts with no fitment entry. No explicit when-to-use/when-not 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?

With no annotations, the description carries the full burden and does disclose several behavioral traits: the call mutates state (creates a request), returns a reference, has a stated turnaround ('Satmarin replies within one working day'), and explicitly triggers no email to the requester. However, it omits auth/permission requirements, duplicate-request behavior, and error handling for invalid or non-quotable parts mentioned in the schema.

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 padding; the core action and return value come first. The final sentence about not emailing the requester is non-obvious and 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 mutating tool with no annotations and no output schema, the description correctly supplies the missing return-value info ('returns its reference') and a latency expectation, plus a nested-object-heavy schema that is well documented. Only auth/permission context is missing, a minor 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?

Schema description coverage is 67% and the description adds no parameter-level detail (it never explains items, contact, or notes). The schema already documents the items array bounds, sku/qty semantics, and notes length, so the description neither compensates for nor extends the remaining gap.

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+resource combination ('Request a formal quotation for catalog parts') and describes the effect ('Creates a quote request and returns its reference'). It does not distinguish itself from siblings like search_parts or resolve_supersession, so the agent must infer the boundary, but the purpose itself 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 description says what the tool does but never states when to use it versus alternatives, nor any prerequisites (e.g., that parts must already be known/quotable, or that search_parts should be used first to find SKUs). Usage is only implied by the verb.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It adds useful context that the tool follows a replacement chain to the latest live product, which is beyond a simple lookup, but omits permissions, error cases, and return format details.

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 core question and followed by the key behavior. It is efficient with no wasted words, though the question format is slightly informal.

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?

Given the lack of annotations, output schema, and parameter descriptions, the description is incomplete for an agent to call the tool correctly. It should explain what parameters to provide and what the return value includes (e.g., discontinued status and replacement details).

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 description makes no mention of the input parameters (sku and product_id), and schema description coverage is 0%. With two entirely undocumented parameters, the description fails to compensate for the schema gap.

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 action (checking if a part is discontinued and following the replacement chain) and resource (part/supersession chain). It clearly distinguishes the tool's core function, though it does not name or contrast with sibling tools like search_parts or check_compatibility.

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. It implies usage when you need to know if a part is discontinued, but does not say when-not or mention 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?

With no annotations, the description carries the full behavioral burden, and it does add genuinely useful ranking behavior ('exact SKU, SKU prefix, title, description'). It does not disclose that this is read-only, whether results are paginated, what an empty result means, or anything about permissions/rate limits.

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 tight sentences, zero filler, with the core purpose front-loaded and the ranking detail second. 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?

For a read-only search tool with no output schema, the description covers purpose, query types and relevance ordering, which is most of what an agent needs. It stops short of describing the result shape or pagination behavior, which the absence of an output schema would otherwise justify including.

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 (query, brand, model, part_type, limit) are already documented in the schema; baseline 3 applies. The description's matching-order sentence adds marginal ranking meaning but no format/syntax 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?

Specific verb ('Search') plus resource ('Satmarin catalog for a part') with the accepted query types spelled out. It is clearly distinct from check_compatibility, get_quote and resolve_supersession, but it never states its relationship to the part-number-adjacent sibling resolve_supersession, so an agent still has to guess which to pick when the query concerns a superseded part.

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 query-type enumeration (part number, model, free text): call it when you have one of those and want to locate a part. There is no explicit when-not guidance, no mention of alternatives, and no hint about what to do when exact matching fails and resolve_supersession might be needed.

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