Deterministic public-web change observation with evidence-bound commercial interpretation.
Scored across 2 tools
Each tool has a completely distinct role: observe_public_page handles deterministic fetching and change detection, while interpret_commercial_change handles semantic interpretation of those changes. No overlap or ambiguity exists.
Both tools follow a consistent verb_noun pattern in snake_case (observe_public_page, interpret_commercial_change). The naming is clear, predictable, and uniformly styled.
With only 2 tools, the server is on the thin side, but the pair forms a complete workflow (observe, then interpret). The narrow scope justifies the small count, though it feels minimal.
The tool surface covers the core lifecycle: observing a page, detecting changes, and interpreting commercial significance. Missing management operations (e.g., listing targets) are minor and not essential to the primary purpose.
SEMANTIC INTERPRETATION over PRICING AND COMMERCIAL-OFFER PAGES ONLY. Requires a target that already has two persisted observations with a deterministic CONTENT_CHANGED verdict; it never refetches the page and never decides whether a change occurred. Input: targetId (returned by observe_public_page), optionally fromObservationId/toObservationId. Returns classified commercial changes (price, plan, discount, availability, packaging...) where every claim quotes observed before/after text, plus rejected claims and their rejection reasons. Uncertainty: unsupported, immaterial, numerically inconsistent or low-confidence claims are discarded. Non-commercial pages return INSUFFICIENT_EVIDENCE with no changes. There is no guarantee that a page contains commercial intelligence. Cost: free beta, model-backed and separately rate limited per credential.
| Name | Required | Description | Default |
|---|---|---|---|
| targetId | Yes | Target UUID from a previous observation. | |
| toObservationId | No | Optional 'after' observation UUID. | |
| fromObservationId | No | Optional 'before' observation UUID. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds substantial behavior beyond annotations: it never refetches, never decides whether a change occurred, discards uncertain or inconsistent claims, and is model-backed and rate limited per credential. Annotations indicate read-only and non-destructive, and the description confirms and expands on this with specific operational details.
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 front-loaded with the core purpose and then packs every sentence with relevant details: input requirements, output structure, uncertainty handling, edge cases, and cost/rate limits. No fluff or repetition detracts from its informativeness.
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?
With no output schema, the description thoroughly covers what to expect: classified changes (price, plan, discount, availability, packaging), quoted before/after evidence, rejected claims with reasons, INSUFFICIENT_EVIDENCE for non-commercial pages, and the caveat that commercial intelligence is not guaranteed. This fully equips the agent to decide when and how to invoke it.
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, but the description adds useful context: targetId comes from observe_public_page, and fromObservationId/toObservationId represent before/after observations. This links the parameters to the intended workflow beyond what the schema's one-line descriptions offer.
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: semantic interpretation over pricing/commercial-offer pages, classifying proven commercial changes. It explicitly distinguishes from the sibling observe_public_page by noting it never refetches and requires prior observations.
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 explicit preconditions: requires a target with two persisted observations and a CONTENT_CHANGED verdict. It also tells when not to expect useful output (non-commercial pages return INSUFFICIENT_EVIDENCE) and references the companion tool observe_public_page for obtaining targetId.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
DETERMINISTIC OBSERVATION. Fetches one lawful public web page and records a bounded representation of it (title, normalized text length, content fingerprint). If the page was observed before, returns an arithmetic comparison against the previous observation: BASELINE_CREATED, NO_CHANGE or CONTENT_CHANGED. Makes no claim about meaning. Input: url (public http/https page). Private, loopback and internal addresses are refused; redirects, response size and timeouts are bounded. Uncertainty: the verdict is arithmetic, not semantic. A CONTENT_CHANGED verdict proves the content differs, not that the difference matters. Cost: free beta, rate limited per credential. No payment capability exists.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Absolute http(s) URL of a lawful, public, non-credentialed page. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true. The description adds substantial behavior beyond this: it states the observation is deterministic, records only a bounded representation, refuses private/internal addresses, bounds redirects/response size/timeouts, and discloses the arithmetic nature of comparison. It also clarifies cost and lack of payment capability. No contradiction with annotations.
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 reasonably concise but dense with information. It is front-loaded with 'DETERMINISTIC OBSERVATION', and every sentence conveys meaningful content about behavior, constraints, or uncertainty. A slight vocabulary/format overhead prevents a 5.
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 there is no output schema, the description fully explains the return values (BASELINE_CREATED, NO_CHANGE, CONTENT_CHANGED) and their arithmetic basis. It also covers restrictions, uncertainty, and cost. For a tool with one parameter and clear behavior, this description is complete and self-contained.
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% (url is described as 'Absolute http(s) URL of a lawful, public, non-credentialed page'). The description adds meaning by explicitly stating that private, loopback, and internal addresses are refused, and by describing how the URL is used (fetched, recorded). This goes beyond the schema's baseline of 3, though it doesn't introduce wholly new parameter semantics.
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 uses a specific verb ('fetches', 'records') and names the resource ('one lawful public web page'). It clearly distinguishes from the sibling tool by stating 'Makes no claim about meaning', positioning it as purely observational rather than interpretive.
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 gives clear context on when to use this tool (for deterministic observation of public pages) and what to expect (arithmetic comparison, not semantic meaning). It does not explicitly name the alternative tool 'interpret_commercial_change' for semantic interpretation, but the contrast is strongly implied. Limitations like private/loopback refusal and rate limiting are provided.
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.
interpret_commercial_changeobserve_public_pagePay-per-call web search, keyword trends, and evidence-backed public-page change intelligence.
Evidence-bearing public webpage monitoring with hashes, diffs, signed webhooks, REST, and MCP.
Read-only public website inspection: evidence-backed Machine Presence observations with uncertainty.
Site & competitor monitoring: snapshots, evidence-backed diffs, briefs, price checks, mentions.
Add one secure layer between your agents and this server.
