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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds genuinely new behavior: that output is truncated on a structural boundary when sections is omitted, which is important context an agent cannot get from annotations or 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 tight sentences, front-loaded with what the tool produces and followed by the operational constraint. 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?

No output schema exists, and the description does characterize the return (a design.md document, possibly truncated). A brief note on cache/refresh interaction or size limits would close the remaining 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 coverage is 100% and the sections enum is fully documented in the schema, so the baseline is 3. The description reinforces that sections is honoured and that omitting it yields everything, but adds no syntax or ordering 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 (render) and resource (a style as a design.md document), which is a distinct output format. However, it never contrasts with the sibling refero_get_style, so an agent must infer which of the two returns what.

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 implied usage guidance around budget (request only the sections you need) and the default full-document behavior, but never states when to pick this tool over refero_get_style or refero_match_style.

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 cover safety (readOnly, idempotent, non-destructive) and open-world access. The description adds the semantic distinction of structured JSON vs. prose, which is useful, but doesn't mention caching behavior or that refresh bypasses cache (that's only in the schema). With annotations already covering the safety profile, this is adequate but not rich.

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: first states what is returned, second routes to the sibling. No waste and front-loaded.

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?

Complete enough for a read-only retrieval tool: it says what data is returned (design system + tokens) and when to use the alternative. It doesn't mention whether results are paginated or cached, but annotations and schema cover most needs.

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%, with descriptions for refresh, style_id, and include_measured_tokens. The description doesn't add parameter detail beyond the schema, so the baseline 3 is appropriate.

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: returns parsed design system and measured tokens as JSON. It names the sibling it is not (refero_get_design_md), which helps an agent distinguish the two retrieval tools.

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 states when to prefer the alternative: use refero_get_design_md when prose is wanted for a document. This directly answers when-to-use-this-vs-sibling.

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 cover safety (readOnly, idempotent, non-destructive, open-world), so the description is freed to add value—and it does, by explaining that published vs. indexed counts can diverge and that misses are expected prior to indexing. It does not describe the return shape, but with no output schema and simple counts, that gap is modest.

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 the core action, then the critical usage constraint. Every clause earns its place; no redundancy or 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 no-param, read-only status tool with no output schema, the description supplies what matters: what is counted and the diagnostic purpose. It would be marginally stronger if it hinted at the expected response fields, but that is a minor gap given annotations already indicate safety and idempotency.

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?

Zero parameters, so baseline is 4 per rubric. The description correctly implies no inputs by describing a purely informational report, adding no confusing parameter hints.

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, concrete purpose: reporting published style count and locally-indexed count. Differentiates from siblings like refero_search_styles and refero_list_style_ids by framing itself as a coverage/diagnostic check rather than 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?

Explicitly names the condition for use: 'Call this before concluding that a style does not exist.' It also preempts the most likely misinterpretation ('a miss usually means it has not been indexed yet'), which is textbook when-to-use 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, openWorld and non-destructive, so the safety profile is covered. The description adds real value beyond that by disclosing the data source (public sitemap) and the return shape (UUIDs with last-modified timestamps), which tells the agent the data may lag behind live pages. It stops short of stating ordering, pagination semantics, or sitemap refresh cadence.

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 return value and its source front-loaded before the usage hint. Nothing repeats the title or annotations.

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, so the description correctly spends words on what is returned (UUIDs plus timestamps). That covers the main gap for a no-required-param listing tool; ordering guarantees and whether unpublished styles are excluded are the only notable omissions.

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%, with limit, offset and updated_since each documented including defaults and bounds, so the baseline is 3. The description only alludes to updated_since via 'last-modified timestamps' and adds no format or behavior 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 and resource ('Return published style UUIDs and their last-modified timestamps') plus the data source ('straight from the public sitemap'). It implicitly separates itself from refero_get_style by noting ids come without reading a style page, but it never names the closest sibling, refero_search_styles, so the boundary between listing and searching is left for the agent to infer.

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 second sentence gives a usage context ('Use this to discover ids without reading any style page'), which implies a cheap discovery workflow. However, it offers no explicit when-not guidance and does not name refero_search_styles as the alternative for filtered lookup, so the choice between list and search remains unstated.

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 cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description adds real value by disclosing the return shape, which matters because there is no output schema, but it stays silent on the side effect of the 'expand' parameter pulling uncached styles into a local index, which affects latency and network behavior.

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 capability statement front-loaded and the routing cue appended. Nothing repeats the title or schema.

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 low-complexity read tool with three well-documented params, the description covers the essentials and compensates for the missing output schema by describing the return payload. It is slightly incomplete on the expand/indexing side effect and on match ordering or scoring.

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 (brief, limit, expand) are already documented with defaults and bounds. The description adds no format or semantics beyond that, which is the expected baseline when the schema does the heavy lifting.

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 ('match a design brief ... return the styles') and even previews the return payload (matches, triggering terms, rationale). It implicitly distinguishes itself from name-based lookups with 'rather than a specific name,' but never names the sibling it displaces.

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 triggering condition ('when the request is qualitative') plus an example query, and implies the when-not case (specific name) without naming the alternative tool. Usable without inference about intent, but routing between refero_search_styles and refero_get_style is left implicit.

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/openWorld, so the safety profile is covered. The description adds genuinely non-obvious behavior: matches occur on word boundaries across names, north-star statements, colours, fonts and URLs, and results improve as the on-demand local index grows.

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 with the core purpose front-loaded; the matching-scope and index-growth details follow in priority order. No filler, though the index note borders on implementation detail an agent may not need.

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, but the description need not describe return shape for a simple search. Combined with 100% schema coverage and read-only annotations, an agent has enough to call it correctly; only explicit sibling routing 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 coverage is 100%, so the baseline is 3. The description goes slightly beyond by explaining that the index grows on demand and that `expand` pulls uncached styles in, which clarifies the otherwise puzzling interaction between the index and the expand parameter.

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 design styles") plus the target site and the input modality (free text). It does not explicitly differentiate itself from siblings like refero_match_style or refero_list_style_ids, so an agent must infer which search variant to pick.

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 "by free text" and the note that the local index grows on demand, but there is no explicit when-to-use versus refero_match_style, nor any exclusion or prerequisite guidance. The agent gets context about caching behavior but no routing rule.

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