Fresh402 helps AI agents save money by detecting meaningful changes in webpages and APIs before expensive browsing, scraping, or LLM processing.
Register a baseline for free, then run on-demand freshness checks for $0.005 USDC via x402 payments on Base.
Supports HTML, JSON, and text, persistent watch IDs, CSS selector filtering, noise reduction, and deterministic diffs. Available through MCP and REST APIs.
Scored across 2 tools
The two tools have clearly distinct roles: fresh402_register creates or retrieves a baseline watch, while fresh402_check checks for changes. The descriptions explicitly clarify the workflow and warn against using register as a free repeated check, leaving no meaningful overlap.
Both tools follow a consistent fresh402_<verb> snake_case pattern. The naming is predictable and easy to parse.
Only two tools are provided, which feels thin for a watch management service. While they cover the core workflow, the surface lacks operations like list, delete, or update, and 2 is below the typical 3-15 range.
The core create-and-check lifecycle is present, but there are notable gaps: no delete, list, or update for watches, and no way to inspect baseline details. Agents cannot manage accumulated watch_ids, matching the 'create+get but no update/delete' pattern.
Check whether a registered or caller-supplied web resource changed. Costs $0.005 USDC. Use fresh402_register first for a free baseline when starting a new watch.
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | ||
| selector | No | ||
| watch_id | No | ||
| include_diff | No | ||
| previous_hash | No | ||
| max_age_seconds | No | ||
| ignore_selectors | No | ||
| ignore_json_paths | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It adds genuinely useful context by disclosing billing ('Costs $0.005 USDC'), which is exactly the kind of trait annotations cannot express. However, it says nothing about whether the check is read-only, how results behave for caller-supplied resources, or how max_age_seconds/caching affects whether a live fetch occurs.
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 with no filler, and the purpose is front-loaded ahead of cost and prerequisite. Every sentence carries distinct, non-redundant information.
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 an 8-parameter, no-annotation, no-output-schema tool, coverage is thin: the description covers purpose, price, and prerequisite ordering but leaves the entire parameter surface and the shape of the change result (changed yes/no, diff, hash) undocumented.
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 8 parameters with 0% schema description coverage, so the description must compensate and largely does not. It only hints at the watch_id-versus-url distinction via 'registered or caller-supplied'; selector, include_diff, previous_hash, max_age_seconds, ignore_selectors, and ignore_json_paths are completely unexplained in both the schema and the description.
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 ('Check whether a ... web resource changed') and scopes it to two modes ('registered or caller-supplied'), which immediately separates it from the sibling fresh402_register that only creates baselines. An agent can tell what the tool does 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?
Names the sibling and the condition that selects it: 'Use fresh402_register first for a free baseline when starting a new watch.' That is real routing guidance. It stops short of explaining when to pass watch_id versus url/selector, and names no exclusions, so it is clear but not complete.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create or retrieve a free Fresh402 baseline and persistent watch_id. Existing baselines are returned without refetching, so this tool cannot be used as a free repeated change check.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| selector | No | ||
| ignore_selectors | No | ||
| ignore_json_paths | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It usefully discloses a non-obvious behavioral trait: existing baselines are returned without refetching (idempotent/cached behavior). However, it omits auth requirements, rate limits, cost implications, and what happens on conflicting selector/ignore inputs.
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?
Two tight sentences, front-loaded with the primary action and followed by an important constraint. Little waste, though the second sentence could be trimmed slightly.
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 four-parameter tool with no annotations and no output schema, the description covers only the caching behavior. It leaves parameter semantics and behavioral context largely unexplained, so an agent would need the raw schema to call it 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?
Schema description coverage is 0% across four parameters (url, selector, ignore_selectors, ignore_json_paths), so the description must compensate but does not. It only references the conceptual outputs (baseline, watch_id) and explains none of the input parameters' meaning or format.
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?
Clear verb+resource: it states it creates or retrieves a Fresh402 baseline and a persistent watch_id. It hints at the sibling's territory (repeated change checks) but never names fresh402_check, so differentiation is implied rather than explicit.
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?
It gives a negative constraint ('cannot be used as a free repeated change check'), which points toward the alternative without naming it. There is no explicit when-to-use statement or reference to fresh402_check, leaving routing to inference.
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.
fresh402_checkfresh402_register
Add one secure layer between your agents and this server.