SKUit Network & Security Catalog

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

Annotations already declare read-only, idempotent, closed-world, non-destructive, so the safety profile is covered. The description then adds substantive behavior beyond that: each result states the single comparison dimension, it is not a drop-in replacement, ambiguous names return candidate families, and each answer carries catalog_url and build_bom_url with an account requirement for the builder.

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?

Purpose is front-loaded and each sentence carries information (ordering rules, presentation caveat, ambiguity handling, return fields). It is a dense single paragraph, slightly long, but nothing is wasted.

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?

There is no output schema, and the description compensates by naming the returned fields (catalog_url, build_bom_url) and the auth prerequisite for the builder. Combined with the ambiguity behavior and the presentation caveat, an agent has everything needed to call and interpret the 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 coverage is 100%, so the baseline is 3, but the description earns extra credit by naming accepted formats ('Cisco 9300X' or 'C9300X-48HX') and confirming the optional vendor prefix, giving the agent concrete invocation guidance the schema's terse string type 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 and resource ('find published alternatives to a product') and scopes the search precisely: one class up, same class, one class down, same vendor first. This is clearly distinguishable from the sibling catalog_search_platforms and catalog_get_platform tools, which search/retrieve rather than compare.

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 a clear usage context (finding alternatives by part number or family, with ordering by class and vendor) and handles the ambiguous-name case. It does not, however, explicitly say when to prefer this over catalog_search_platforms or catalog_get_platform, so the agent must infer the boundary from the sibling names.

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 destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: the payload carries catalog_url and a build_bom_url, and that the SKUit builder requires an account — an auth prerequisite an agent would otherwise not know.

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, front-loaded with the action and key requirement, then the return-value context. No filler or restated title text.

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 names the two significant return fields and the account requirement for the builder, which is more than most get-style tools offer. A brief note on what happens for an unknown/non-exact id would make it complete.

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 the single parameter already documents itself with an example ("C9300X-48HX"). The description's "exact platform id" reinforces strictness but adds no format or syntax detail 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?

Names a specific verb and resource ("Get the published facts for one platform") and pins the lookup key ("exact platform id"). The phrase "as returned by the other catalog tools" cleanly distinguishes it from the sibling search/find tools, which take looser criteria.

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?

Explicitly says the id must be exact and comes from the other catalog tools, which routes the agent through search first. No explicit when-not-to-use or failure-mode guidance (e.g. unknown id behavior), so it stops 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 only cover read-only/idempotent safety, which the description does not repeat; instead it discloses the ranking algorithm (spare ports, then rack units, then headroom), the caveat payload, the aggregate counts, nearest-miss reporting when nothing fits, and the build_bom_url account requirement. This is unusually rich behavioral context beyond the structured fields.

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?

Single dense paragraph that front-loads the purpose and ranking rule before the result-payload detail, with essentially no filler. It is on the long side, but every clause carries information an agent can act on.

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?

There is no output schema, yet the description accounts for the return shape — fit explanation, caveats, meeting/unevaluable counts, nearest misses, and the two URLs — plus the account requirement for the builder. For a read-only search with 100% schema coverage, nothing an agent needs to call it correctly 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?

Schema description coverage is 100%, so all seven parameters are already documented in the schema and the baseline is 3. The description adds only an illustrative demand example (60×100G plus 4×400G), which conveys intent but no new syntax or constraint 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 (Find) and resource (published platforms) scoped by a clear criterion (can serve a port demand), and the ranked-search behavior is plainly distinct from catalog_get_platform (single lookup) and catalog_find_alternatives. An agent knows immediately this is the demand-driven search entry point.

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 clear context for when to reach for it — when you have a port demand and want the closest-fitting published platforms — and tells the agent what to do with the results (pass caveats on to the user). It never names an alternative tool or states a when-not condition, so it stops short of full routing guidance.

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