Five-trial reaction-time summary and links to browser-based reaction tests.
Scored across 2 tools
Each tool has a clearly distinct purpose: one locates a browser test page, the other computes a median from user-supplied reaction times. There is no overlap in functionality or arguments, so an agent can easily select the right tool.
Both tools use snake_case and follow a verb_noun pattern (find_reaction_test, summarize_reaction_trials). The convention is consistent throughout the server.
With only two tools, the set feels thin for a server named ReactionMetric; it covers just finding a test and computing one statistic. While the count is not excessive, it is borderline under-scoped for a domain that could include test execution, validation, or additional metrics.
The server provides only a way to locate a test and summarize five trials into a median. Missing operations include any actual test execution, input validation, or additional summary statistics, so the surface is notably incomplete for a reaction time metric tool.
Find the matching ReactionMetric browser test page.
| Name | Required | Description | Default |
|---|---|---|---|
| test | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full behavioral burden, and it discloses almost nothing. "Find" weakly implies a read-only lookup, but there is no statement about side effects, permissions, or what the returned page actually is.
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?
It is a single short sentence with no filler, so it is concise. The brevity is under-specification rather than efficiency, and there is no structure to front-load usage context.
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 one-enum-parameter tool with no annotations and no output schema, the description should at least explain what a "ReactionMetric browser test page" is and what the enum values represent. It omits both, so an agent cannot confidently interpret the result.
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?
The single parameter has an enum (reaction, reflex, double_click, cps, f1, sound, keyboard) but schema description coverage is 0%, so the schema documents nothing about their meaning. The description adds no explanation of what these test identifiers select, so the opaque enum values remain unmapped.
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 ("Find") and resource ("ReactionMetric browser test page"), so the basic action is clear. However, "matching" is undefined (matching against what?) and it never contrasts itself with the sibling summarize_reaction_trials, leaving the boundary between the two tools to inference.
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?
There is no statement of when to use this tool, when not to, or how it relates to summarize_reaction_trials. An agent must guess whether this retrieves a page definition versus trial results.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Calculate a transparent median of five user-supplied valid browser-observed reaction times in milliseconds; no calibration or population percentile claims.
| Name | Required | Description | Default |
|---|---|---|---|
| trials_ms | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It usefully discloses the algorithm intent ('transparent median', i.e., plain median, not a trimmed/calibrated estimate) and a negative scope (no percentile claims), but says nothing about output format or error behavior for invalid input.
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?
A single front-loaded sentence with the verb and resource first, then the scope caveat. Every clause earns its place with no filler.
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 small computation tool with no output schema and no annotations, the description is adequate on input and scope but omits what is returned (the median value) and how invalid or out-of-range input is handled. Enough to call it, but not fully complete.
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 for the single parameter, and it does: it conveys count (five), unit (milliseconds), and qualifying semantics (user-supplied, valid, browser-observed). This meaningfully enriches the bare 'trials_ms' array.
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 (Calculate) and resource (median of five user-supplied reaction times in ms), so the operation is unambiguous. It does not, however, reference the sibling find_reaction_test or otherwise differentiate the two, keeping it below a 5.
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 is only implied by the computation itself; there is no explicit when-to-use, no named alternative, and no prerequisites. The 'no calibration or population percentile claims' clause hints at an exclusion, but it reads as a scope disclaimer rather than routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
find_reaction_testsummarize_reaction_trialsCheck whether AI assistants can reach, read and cite a public website. No account for 4 of 5 tools.
Measured rates at which web services lack machine-readable capabilities. Research demonstrator.
Human tests for agent-built websites. Free early access now. Planned $5 pilot; paid orders closed.
Measures your site in a real browser and returns verifiable observations, with evidence and limits.
Add one secure layer between your agents and this server.