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

With no annotations provided, the description carries the full behavioral burden, and it delivers one genuinely useful disclosure: the default response is the entire document, truncated on a structural boundary. That truncation semantics is non-obvious and would otherwise surprise an agent. It does not address read-only status or caching (refresh is only covered in the schema), so it is strong but not complete.

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, no filler, and the core purpose is front-loaded before the parameter guidance. Every clause carries actionable information (what it renders, why to pass `sections`, what happens without it).

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 three-parameter, no-annotation tool with no output schema, the description adequately characterizes the output (a design.md document, possibly truncated) and the parameter-driven scoping. The only meaningful gap is that cache/refresh behavior and read-only nature are left entirely to the schema.

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 meaning beyond the schema: it frames `sections` as a budget-control mechanism and states the fallback behavior when it is omitted. The schema's enum list and the default are documented structurally; the description supplies the rationale and the truncation consequence.

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 verb and output artifact: 'Render a style as a design.md document.' That is more specific than the sibling refero_get_style, since it tells the agent the result is a markdown document rather than a raw style record. It stops short of explicitly contrasting itself with those siblings, but the resource/format 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?

Usage is implied rather than stated: the mention of staying 'within budget' hints that this tool is for budget-sensitive section retrieval, and the default whole-document behavior is noted. There is no explicit when-to-use versus refero_get_style or refero_search_styles, and no stated preconditions, so guidance remains inferential.

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. It discloses the return payload and notes the data is scraped from the live site (implying network fetch), but says nothing about read-only nature, auth requirements, rate limits, or the cache/refresh behavior that the schema hints at. Useful context, but incomplete for a no-annotation tool.

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 what is returned and immediately followed by the alternative-tool routing. No filler or restatement of the title.

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 and no annotations, the description must explain the return value, and it does so reasonably by naming the token categories and JSON format. Caching/refresh semantics and failure modes are left to the schema, which is acceptable for a simple three-parameter get-by-id tool, though a note on the read-only/cached nature would round it out.

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 three parameters are already documented in the schema. The description implicitly connects to two of them (measured tokens, live-site scraping) but adds no syntax, defaults, or format detail beyond what the schema supplies, so the baseline 3 holds.

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 verb (return) and resource (the parsed design system plus measured tokens scraped from the live site) and enumerates the payload contents (colours, fonts, radii, spacing). It also explicitly distinguishes itself from the sibling refero_get_design_md, so an agent can pick between the two without opening a schema.

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 a clear routing rule: prefer refero_get_design_md when prose is wanted for a document, which implies this tool is for structured/JSON consumption. It does not address the other siblings (search_styles, match_style, list_style_ids) or state explicit when-not conditions, but the primary alternative is covered.

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 it delivers the key behavioral fact: a search miss typically means the style is unindexed rather than absent, and it discloses that two counts are returned. It omits freshness/staleness of the index and cost of calling, so it is strong but not exhaustive.

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, zero filler, with the output content stated first and the critical usage caveat immediately after. Nothing is redundant or padded.

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 and no annotations, the description must stand alone, and it explains both what is reported and how to interpret a negative search result. It does not specify the returned field names or index refresh behavior, which is a minor remaining gap for a zero-param read 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?

The tool takes zero parameters, so there is no parameter semantics to explain and the baseline of 4 applies. The description correctly implies a no-input status query.

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 (report) and resource (counts of published vs locally indexed styles), which is clearly distinct from the search/get/match siblings. It never names a sibling explicitly, so it stops short of the 5-level contrast, but no agent would confuse it with a retrieval 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?

Gives an explicit call condition: invoke this before concluding a style does not exist, because a miss usually signals pending indexing. That directly routes the agent's decision after a failed lookup, which is exactly the guidance a status tool needs.

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 supplied, so the description carries the burden, and it does disclose the data source (public sitemap) and the shape of the return (UUIDs plus timestamps) plus the read-only, lightweight nature. It omits pagination/rate behavior and what happens on an empty result, so the disclosure is partial.

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 with zero waste; the what is front-loaded and the intended use follows immediately.

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, but the description names exactly what comes back (UUIDs and last-modified timestamps), which compensates adequately for a simple listing tool. Only minor gaps remain around pagination and default/empty-result 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 coverage is 100%, so limit, offset, and updated_since are already fully documented in the schema; the baseline of 3 applies. The description adds no syntax, format, or interaction details beyond what the schema provides.

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: returns published style UUIDs plus last-modified timestamps. The 'without reading any style page' clause hints at how it differs from page-reading siblings like refero_get_style, but no sibling is named 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?

Intended usage is implied ('discover ids'), which is enough to infer this is a lightweight discovery step before fetching a style. There is no explicit when-not guidance and no named alternative such as refero_search_styles for filtered discovery.

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 must carry behavioral disclosure. It usefully reveals the return shape (matches plus triggering terms and rationale), which is real value, but it says nothing about whether the call is read-only, how caching/`expand` affects latency, or any cost implications.

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 with zero filler: the first states what is returned, the second states when to reach for it. The routing condition is front-loaded after the core 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?

No output schema exists, so the description responsibly summarizes the return (styles, triggering terms, rationale). The remaining gap is the caching/`expand` behavior and any latency or freshness caveat, which the schema alludes to only through a parameter.

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 the schema already documents `brief`, `limit`, and `expand` with defaults and bounds. The description adds no parameter-level meaning beyond that, so the baseline of 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 (match), the input (a prose design brief), and the resource (Refero styles), plus describes the return payload (matched styles with triggering terms and rationale). It does not name the closest sibling (refero_search_styles) directly, so the differentiation is implied rather than explicit.

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 selection condition: use it when the request is qualitative ("I need a dense, data-heavy dashboard") rather than a specific name. This implicitly routes name-based lookups elsewhere, but it never names the alternative tool or states explicit when-not conditions.

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 full burden and does add real context: word-boundary matching across names/statements/colours/fonts/URLs, and the note that the local index grows on demand so results improve as more styles are indexed. It omits auth requirements, rate limits, and return shape, which keeps it short of a 5 but it is well above the bare minimum.

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, front-loaded with the verb+resource, then matching behavior, then the index caveat. Every sentence adds information with no padding, though it could be marginally more compact.

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 no annotations, so the description bears extra weight. It covers what is searched and the index behavior but never describes what a result looks like or whether results are paginated, leaving a gap for a search 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 description coverage is 100%, so all three parameters (query, limit, expand) are already documented in the schema, establishing the baseline of 3. The description adds only marginal value by explaining the index-growth behavior tied to expand, but no syntax or format 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?

States a specific verb+resource ('Find design styles on styles.refero.design by free text') with the exact domain and search modality, so an agent knows what it does. It does not explicitly differentiate itself from the sibling refero_match_style, which also sounds search-like, leaving mild overlap ambiguity.

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 when-to-use, when-not, or alternative guidance is given. With a sibling named refero_match_style and refero_get_style, the description never explains which one to pick for a given intent, forcing the agent to infer.

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