EuroA11y

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

Annotations already cover safety (read-only, idempotent, closed-world), so the description's added value is the domain behavior: the 28 June 2025 applicability date, the <10 employees / EUR 2m thresholds, the 2016/2102 overlap for public bodies, and the instruction to ask rather than guess. The 'informational, not legal advice' disclaimer is also useful framing. Slight gap: it doesn't hint at what the verdict/sources output contains, though an output schema exists.

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-loads the trigger condition and the legal instrument before any detail, and every clause carries content (date, thresholds, per-service rule, no-guessing rule, disclaimer). Dense but not padded; the parenthetical French title is slight surplus for most agents.

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?

Output schema exists so return values needn't be described, and the description supplies everything else an agent needs to invoke correctly: trigger, granularity (one call per service), input-gathering behavior, effective date, and the informational-advice boundary.

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 earns the uplift by restating the operative thresholds (fewer than 10 employees, turnover or balance sheet not above EUR 2 million) that drive the exemption logic and by naming the two parameter families that matter – headcount/financials and public-body status – which the schema documents individually but not as a decision rule.

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 precise check – whether the EAA (Directive (EU) 2019/882) applies – and names the exact decision factors: covered consumer services, the microenterprise exemption, and public bodies. An agent can tell immediately this is a scoped legal-applicability determination, not a general search or page scan.

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 says when to use it (user asks about applicability to their business/website), gives concrete examples (online shop, bank, transport operator), instructs one call per service for multi-service businesses, and explicitly prefers itself over a web search. That covers when, how many times, and versus the obvious alternative.

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 read-only, idempotent, open-world behavior, and the description still adds meaningful context beyond them: runtime (5 to 30 seconds), result caching including how to bypass it (fresh: true with a 5-minute threshold), the structure of the return payload, and the explicit limits of an automated scan. That is exactly the extra context the lower bar with annotations asks for.

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 usage trigger, then behavior, then a single-constraint close. It is fairly dense at roughly 140 words, but every sentence carries information an agent needs; the only mild redundancy is restating the return payload when an output schema already exists.

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 6-parameter scan tool with annotations and an output schema, the description covers trigger, duration, caching, scope limits and per-call cardinality. Nothing an agent needs in order to call it correctly 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 would be 3, but the description adds real semantics by tying `fresh` to the caching rule ('A recent result of the same page may be reused (reused_until); fresh: true scans it again') and by stating the one-page-per-call constraint. The remaining parameters (viewport, include_rgaa, max_examples, include_best_practices) are left entirely to 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 ('Loads one public web page in a real browser and runs axe-core against WCAG 2.2 level AA'), which distinguishes it cleanly from sibling check_eaa_scope and from 'reading the page source'. An agent knows exactly what it produces without opening the 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?

Opens with an explicit trigger ('when a user asks to audit, check or test the accessibility of a website or web page'), names the standards and page types, gives a prefer-it-over alternative ('Prefer it to reading the page source: it tests the rendered page'), and closes with a cardinality rule ('One page per call: call it again for each other page').

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