SwiftSkills

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real value beyond them: it enumerates returned fields, notes that copied_at is conditional ('when the catalog recorded the day'), that license is 'when known', and warns that URLs carry utm_source=mcp/utm_medium=tool tracking parameters.

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-loaded with the core action in the first sentence, followed by a return-field list. Efficient overall, though the field enumeration plus the utm note makes the second half dense for a simple lookup tool.

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 responsibly describes what comes back, which covers the main completeness gap. It omits only edge behavior such as not-found handling, which is minor for a simple idempotent read.

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 0% for the single slug parameter, so the description must carry the semantic load. It does convey that slug is the identifier of exactly one entry, but adds no format guidance (case, hyphenation, or whether a name/ID is accepted) and does not explain failure when no entry matches.

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 plus the lookup key: 'Fetch one public catalog entry by slug.' The word 'one' plus 'by slug' implicitly distinguishes it from the list/search siblings, though none of them are named.

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: 'by slug' signals the precondition that you must already know the identifier, which in turn implies discovery flows belong to search_entries or list_new. No explicit when-to-use or when-not-to-use statement and no sibling is named.

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 by structured data. The description adds one piece of genuinely useful context beyond the schema: that returned urls carry utm_source=mcp and utm_medium=tool, which tells the agent the links are MCP-attributed. It says nothing about result size, ordering, or pagination.

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 zero filler; the resource and returned fields come first and the utm attribution detail is secondary. Every clause carries information, and nothing needs to be trimmed.

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 no-argument, read-only listing tool with no output schema, the description supplies the key missing piece: what each result contains (slug, name, url) and the utm tagging on those urls. Full marks would require some hint about result scope or ordering, but the definition is otherwise sufficient to invoke the tool correctly.

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 has zero parameters, so according to the rubric the baseline is 4. The input schema is an empty object and there is nothing further for the description to disambiguate.

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 ('List') plus resource ('catalog categories') and enumerates the returned fields (slug, name, url), which is more than a restatement of the title. It does not explicitly distinguish itself from siblings like search_entries or list_new, but the resource noun is distinct enough that an agent can tell them apart.

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 contains no when-to-use or when-not-to-use guidance and never mentions the sibling tools (get_entry, list_new, search_entries) or the conditions that would select one over another. Usage is only inferable from the fact that the tool takes no parameters, which is exactly the 'no guidance' case rather than explicit 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 readOnly, idempotent, non-destructive behavior, so the description need not restate safety. It adds genuinely new behavioral context: the default/max window, newest-first ordering, and the exact fields and utm parameters present in each row's URL.

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 tight sentences: scope and ordering first, return fields second, URL detail third. No filler and every clause contributes 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 usefully enumerates returned fields (name, slug, type, category, summary, url, added) and notes the utm tracking parameters. Annotations already cover the safety profile, so the remaining description is appropriately 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 coverage is 0% and the schema only carries maximum: 90, so the description's statement of the default (7) and the upper bound (90) adds real meaning beyond the schema. It is the only source of the default value.

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 (list) and resource (entries) with a precise scope: added within the last N days, newest first. It implicitly differs from search_entries by being a recency filter, but it never names a sibling to differentiate 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 is implied by 'added within the last days' — clearly the tool for recent additions — but there is no explicit when-to-use/when-not guidance or mention of the alternatives (search_entries, get_entry) that an agent should weigh.

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, and non-destructive, so the safety profile is covered. The description adds meaningful behavior beyond that: a 50-row cap with total counting the remainder, and that every returned url carries utm_source=mcp and utm_medium=tool — details an agent could not infer from 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?

Five short sentences, each carrying distinct information, with the core search behavior front-loaded before result-shape and pagination details. 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?

With no output schema, the description compensates by naming the returned fields (name, slug, type, category, summary, url) and the truncation behavior (50 rows plus a total). An agent has everything needed to call it and interpret results.

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 0% and has no enums, so the description carries the full burden — and it delivers: query is defined as a case-insensitive substring (max 200), category as an optional slug, and type's allowed values (skill, mcp, rules, docs, sdk) are enumerated only here. It stops short of explaining how category/type interact or the matching behavior for those filters.

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 (Search) and resource (public SwiftSkills catalog), and the parameter list clarifies the search surface. It does not explicitly contrast with siblings like get_entry or list_new, but 'search' vs 'get'/'list' is reasonably self-distinguishing.

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 (keyword search with optional category/type filters) but never states when to choose this over get_entry for a known item or list_new for recency. No exclusions or alternative routing are provided.

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