Draft a German accessibility statement (Erklärung zur Barrierefreiheit) for a website, optionally enriched with a previous scan_accessibility result. Missing legally-required facts come back as [[PLACEHOLDERS]] you must fill in; the draft needs legal review before publication. Pure text generation, no network access. 200 credits, requires an API key.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| scanResult | No | ||
| contactEmail | No | ||
| organisation | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full responsibility. It discloses that this is pure text generation (no network access), that missing facts become placeholders, that legal review is required, and that it costs credits and needs an API key. This is exceptionally transparent and goes beyond basic purpose.
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 two sentences long, front-loaded with purpose, and covers usage, behavior, and constraints without fluff. Every sentence earns its place.
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's complexity (4 params, nested object, no output schema, no annotations), the description covers the key aspects: purpose, optional input, placeholders, legal caveat, and access requirements. It does not explicitly state the output structure or error handling, but for a text-generation tool this is acceptable.
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 0%, so the description must compensate. It mentions the optional scan_result but does not explain the purpose of url, contactEmail, or organisation. While parameter names are self-explanatory, the description does not provide meaningful additional semantics for each 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?
The description clearly states the tool's function: drafting a German accessibility statement for a website. It uses a specific verb ('Draft') and resource, and distinguishes itself from the sibling tool 'scan_accessibility' by mentioning optional enrichment with a previous scan result.
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 context is clear: this is for drafting after scanning, optionally using scan_accessibility results. It implies the tool should be used in conjunction with scanning, but does not explicitly state when not to use it or name alternatives. Still, the guidance is sufficient for an agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The two tools are completely distinct: one performs a technical accessibility scan, the other generates a legal statement. No overlap or ambiguity exists.
Both tools follow the same verb_noun pattern: scan_accessibility and draft_statement. Clear and predictable naming.
With only 2 tools, the set feels thin, but the niche scope (accessibility scanning + statement drafting) makes the count appropriate. It's on the low end of the acceptable range.
The workflow is complete: scan a URL, optionally use results to draft a statement. No obvious missing operations for the stated purpose.