Axcess — Design Accessibility Evaluation

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

Annotations declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds substantial behavioral context beyond annotations: it explicitly notes the cost ($0.01 USDC via x402 on Base-compatible EVM network per call), describes the evaluation criteria (specific WCAG standards), and details the return report structure. This exceeds the baseline for annotation coverage, providing rich context about what happens during the call and what the output includes.

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?

The description is well-structured with clear sections: overview, cost disclosure, detailed check list, argument guidance, and return value summary. It front-loads the purpose and cost, then enumerates checks in scannable bullet-like lines. Every sentence serves a purpose, and the formatting (blank lines, line breaks) aids readability without being verbose.

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?

Given the tool has no output schema, the description thoroughly compensates by describing the structured report (per-element scores, severity levels, WCAG references, fix recommendations, overall verdict). It also covers input requirements and example property combinations, making it complete for an agent to invoke correctly. The description is comprehensive despite the absence of an output 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 description coverage is 100%, so the schema already documents all parameters well. The description adds value by explaining the purpose of each parameter group ('Provide width_px/height_px for touch target checks', 'Provide uses_color_only + secondary indicator flags'), giving practical guidance that the schema alone doesn't convey. It also clarifies the requirements for the elements array items, enhancing semantic understanding.

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 clearly states the tool evaluates UI elements for accessibility issues, with a specific verb and resource. It distinguishes itself from siblings by specifying it catches issues that automated scanners (axe/Lighthouse/WAVE) miss, which separates it from the sibling evaluate_typography and list_capabilities.

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?

Provides explicit context on what it checks (design-stage issues beyond automated tools) and gives concrete guidance on required versus optional element properties ('Each element requires: element_type. Provide width_px/height_px for touch target checks...'). This makes it clear when to use this tool vs alternatives like typography evaluation, and how to structure input for relevant check categories.

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, and destructiveHint=false, so the safety profile is established. The description adds valuable behavioral context: a per-call cost of $0.05 USDC on a Base-compatible EVM network and the tool's emphasis on subjective design evaluation rather than pure numeric checks. This goes beyond the annotations.

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?

The description is well-organized with a clear first sentence, cost notification, bulleted capabilities, parameter list, return format, and example. It is somewhat lengthy but every section serves a purpose; the bullet list of issues clarifies the tool's value without being redundant. A small deduction for verbosity.

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?

Given there is no output schema, the description explicitly and thoroughly details the return structure (per-element scores, issues, WCAG references, fix recommendations, overall verdict). It also covers cost, a usage example, and parameter requirements. This is complete for a tool of this complexity.

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 all parameters. The description's Args section repeats the schema's information (e.g., array size, required fields) without adding new semantics. Per the rubric, a baseline of 3 is appropriate when the schema carries the full burden.

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 opens with 'Evaluates typography elements against a principled accessibility rubric' – a specific verb and resource that clearly defines its scope. It distinguishes itself from sibling tools by focusing on typography-specific design judgment and explicitly contrasts with generic automated checkers (axe/Lighthouse/WAVE), making its unique role clear.

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 provides clear context for when to use the tool: when design judgment beyond numeric compliance is needed, with a concrete example workflow via get_design_context. However, it does not explicitly state when not to use it or directly contrast with the sibling evaluate_accessibility tool, so it falls 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 already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable non-schema context: the tool is FREE, while all evaluation tools require USDC payment on Base network. It also discloses the return format (JSON with descriptions, pricing, rubric categories). No contradictions with annotations.

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, each adding necessary information: what it returns, when to use it, and the payment/free distinction. No filler or redundant content. Front-loaded with the main purpose.

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 zero-parameter, read-only catalog tool, the description is fully complete. It covers purpose, usage timing, pricing model, and return contents. Combined with annotations (read-only, idempotent, non-destructive), an agent has all needed information to invoke 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?

There are zero parameters, so the input schema provides no param details. The description compensates by describing the output (tool descriptions, pricing, rubric categories), giving the agent enough understanding of what the tool returns. A score of 4 is appropriate for a no-param tool where description explains 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?

The description clearly states the tool 'Returns available evaluation tools, what they check, and their pricing.' This is a specific verb+resource that uniquely identifies a catalog/list tool, distinct from sibling evaluation tools like evaluate_accessibility or evaluate_typography.

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 instructs 'Call this first to understand what Axcess can evaluate and how much each evaluation costs.' This tells the agent exactly when to use the tool and implies it is a prerequisite before running evaluations. It effectively differentiates from the sibling evaluation tools.

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