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

Beyond the readOnly/openWorld/idempotent/destructive annotations, the description discloses that nothing is persisted, that URL fetching and browser rendering are server-side opt-ins, and that the report includes an explicit list of what the audit cannot verify. That last point is genuinely useful behavioral framing an agent would not infer from annotations. It stops short of noting whether the audit is deterministic or how partial HTML is handled.

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 sentences, front-loaded with the action and result, then the no-storage guarantee and opt-in caveats. Every sentence carries information, though the closing opt-in sentence slightly duplicates the schema's url and mode descriptions.

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 takes on the job of describing return shape (guideline id, severity, evidence, fix, plus a list of unverifiable items), which is exactly what an agent needs. All five optional parameters are covered by the 100%-covered schema, and the destruction/storage question is answered outright.

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 every parameter is already documented with limits and env-var gating. The description adds only a light restatement ('a fetched URL, when the server allows it') and no new meaning about interactions between html and url, or what maxTokens trades off. 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?

The description names a specific verb and resource ('Check submitted HTML ... against the pinned web-interface guidelines') and describes the return payload (findings with guideline id, severity, evidence, fix). It separates itself from taste_guidelines/taste_get by framing this as an evaluation rather than a retrieval, though it never names a sibling 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 context is implied through the opt-in caveats: URL auditing only when the server sets TASTEPRO_AUDIT_ALLOW_URL_FETCH, browser mode only with TASTEPRO_AUDIT_BROWSER, and default static parsing. There is no explicit statement of when to pick this over taste_guidelines or taste_search, nor any exclusion beyond the server flags.

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 non-destructive, so the safety profile is covered; the description adds real value on top with the default token budget (2400) and the includeBody behavior that returns a full document instead of an excerpt. It does not disclose truncation behavior when the budget is exceeded, which would be the remaining useful detail.

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 and sequenced guidance in four short sentences with no filler. The closing 'Default budget 2400 tokens' duplicates the maxTokens schema description, a small redundancy.

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 four simple flat parameters, the definition covers invocation, projection choice, and budget. The main gap is that nothing describes the shape or fields of a returned pack, which matters since there is no output schema to lean on.

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 genuinely extends meaning: it maps each format enum value to a use case, whereas the schema only says 'Response projection'. It also clarifies includeBody applies to references specifically. The budget default restates the schema and adds nothing.

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 ('Fetch one or more packs by id') and ties it to the sibling 'taste_search' as the preceding step. It never spells out what a 'pack' contains or how it differs from taste_guidelines/taste_audit output, so sibling differentiation is only partial.

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 explicit sequencing ('after taste_search') and routes format choice by intent: brief for decisions, full/markdown for implementation detail, json for raw data. It stops short of saying when not to use this tool (e.g. when a search result alone suffices).

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 establish this as a read-only, idempotent, non-destructive, closed-world query, so the safety profile is covered. The description adds that the ruleset is 'pinned' and totals 104 rules, which is useful context about result stability and corpus size, but says nothing about response shape, truncation, or how maxTokens interacts with limit.

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 in the first clause, which is good, but the first sentence then devolves into a seventeen-item keyword list of categories. The second sentence largely duplicates the format and severity enum descriptions already present in the schema, so part of the text does not earn its space.

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 six optional parameters, full schema coverage, and no output schema, the description covers the basics but leaves real gaps: whether 'query' is semantic or keyword matching, whether maxTokens truncates results, and above all how this differs from three overlapping sibling tools. Those omissions matter for a retrieval tool in a crowded namespace.

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 six parameters including defaults are already documented in structured form. The description's 'format=markdown for a checklist' and 'severity=error for must-fix' restate what the schema descriptions already say, adding essentially no new semantics. 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 and resource: querying a pinned corpus of 104 Web Interface Guidelines rules, and enumerates the topic coverage. An agent knows exactly what content comes back, but the description never distinguishes this corpus-retrieval tool from sibling tools taste_search, taste_get, or taste_audit.

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?

Offers how-to-call guidance (format=markdown for a checklist, severity=error for must-fix) but never says when this tool is the right choice versus taste_search, taste_get, or taste_audit. Usage is inferable from the topic list rather than stated as an explicit routing rule.

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, non-destructive, and closed-world, so the safety profile is free. The description adds real context beyond that: results are compact cards with ids (not full content), the default token budget is 1400, and taste_get is required to expand. It does not cover pagination or what happens when the budget truncates results.

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 sentences with no padding: capability, entry-point rule, return shape plus escalation path, then the filter surface. The most decision-relevant facts (use first, compact cards, need taste_get) are 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?

For a nine-parameter, zero-required search tool with no output schema, the description covers the entry-point role, the return shape (cards with ids, not full content), the budget default, and the escalation sibling. What is missing is minor: no note on how token budget affects truncation or on total-result counts.

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 explains kind, domain, quality, source, and budget. The description's 'Filters: kind, domain, quality, source' merely enumerates a subset and leaves query, limit, maxTokens, includePlanned, and includeIncomplete to the schema. With the schema doing the heavy lifting, 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?

States a specific verb ('Search') plus a concrete resource ('TastePro's catalog of design directions, palettes, type pairings, hero/section blueprints, brand analyses, domain playbooks, and references'). The second sentence gates it against the sibling tool by naming taste_get as the follow-up for the full pack, so an agent can distinguish it without opening either 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?

'Use this first for any visual brief' gives an explicit entry-point rule, and 'call taste_get for the full pack' defines the search-then-fetch sequencing. It stops short of naming when taste_guidelines or taste_audit would be preferable, so the exclusion side is only partially covered.

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