Interaction-design laws with their formulae, sources, and design implications — Fitts, Hick, Jakob, Tesler, Doherty. Includes the common misapplications, since these are misquoted more often than they are wrong. Separate from the effects corpus because these are engineering constraints, not contested empirical claims. Free — this call costs nothing. No account or payment required.
| Name | Required | Description | Default |
|---|---|---|---|
| search | No | ||
| with_formula | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries the burden. It mentions the call is free and no account required, implying no side effects or costs. However, it does not explicitly state that the tool is read-only or describe any behavioral aspects beyond being free.
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 concise, with no superfluous words. It front-loads the core topic and key differentiators. Every sentence adds value.
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 parameter count of 2, no output schema, and 0% schema coverage, the description is insufficient. It does not explain the return format, what the output contains (e.g., full list or filtered), or how to use the parameters effectively. The tool's simplicity suggests more could be provided.
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. The description mentions specific heuristics (Fitts, Hick, etc.) but does not explain how the 'search' or 'with_formula' parameters work. For instance, it's unclear if 'search' filters by heuristic name or concept, and what 'with_formula' does. The description adds minimal value over 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?
The description clearly states it provides interaction-design laws with formulae, sources, and design implications, and explicitly distinguishes from the effects corpus. The tool name 'psych_heuristics' aligns with this purpose. However, the description is more about content than the action the tool performs (e.g., retrieve or list).
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 explicitly separates this tool from the effects corpus, stating 'these are engineering constraints, not contested empirical claims,' which guides when to use it vs siblings. It also notes the tool is free with no account needed. However, it does not explicitly state when not to use it or alternative tools for related tasks.
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.
All 20 tools have clearly distinct purposes, grouped by domain prefixes (content_ai, design_ai, legal, psych, ref, tollmint, web). Even similar-sounding tools like psych_dark-pattern-detect and psych_dark-patterns are differentiated as a live scanner versus a reference taxonomy. No two tools overlap in functionality.
Naming mostly follows a prefix_descriptive pattern, but some tools use hyphens (content_ai-score, design_ai-slop-detect) while others use underscores (legal_accessibility, psych_biases). This minor inconsistency prevents a perfect score, but the pattern is still clear and readable.
20 tools is slightly above the typical 'well-scoped' range, but each tool serves a specific, justifiable need across multiple domains (legal, psychology, content analysis, geocoding, internal). The count feels comprehensive rather than bloated.
The tool surface covers all major areas implied by the domain prefixes: comprehensive legal compliance references, extensive psychology/behavioral design tools, content and design analysis, geocoding, and internal server management. No obvious gaps for the intended use cases.