Cross-session idempotency, URLs as schema-validated JSON, and a record of missing capabilities.
Scored across 3 tools
Each tool has a clearly distinct purpose: check_and_claim handles idempotency and cross-session claims, fetch_structured handles URL retrieval and parsing, and request_capability records unmet tooling needs. There is no meaningful overlap or ambiguity between them.
All three names are lowercase imperative verbs with underscore separators, which is consistent. The minor deviation is that request_capability is verb + noun, fetch_structured is verb + adjective, and check_and_claim is a compound verb phrase, but the pattern is still readable and predictable.
Three tools is well-scoped for a focused rescue utility server: each tool addresses a distinct failure mode rather than adding redundant surface area. The count feels intentional and each tool earns its place.
For its stated purpose, the surface is complete: check_and_claim covers atomic claims with clear outcomes, fetch_structured provides both structured extraction and a degraded fallback, and request_capability handles the missing-capability case. No obvious lifecycle gaps or dead ends are apparent.
Atomically check whether an action identified by a key was already performed, and claim it if not. Use it before performing a non-idempotent action that may have completed in an earlier attempt (a payment, a message, a write), or when you need to remember something across sessions. Returns 'claimed' if you are first and 'already_done' if not. Do not use it as a general data store or as a result cache.
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | Stable identifier for the action, e.g. 'invoice-2026-07-A491:pay'. | |
| metadata | No | Small payload returned alongside the claim. Do not include secrets. | |
| ttl_seconds | No | How long the claim lasts, in seconds. Default 86400 (1 day), max 30 days. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It explains atomicity, return values ('claimed' and 'already_done'), and the intended context. It does not detail error behavior or persistence specifics, but the TTL parameter is documented in the schema.
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 three sentences long, with the core action stated first, followed by usage context and return values. It is concise, front-loaded, and contains no redundant or filler content.
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?
Despite having no output schema, the description explicitly states the possible return values. Combined with full parameter coverage in the schema and clear usage/anti-usage guidance, the description is complete enough for an agent to select and invoke the tool 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?
The input schema already covers all three parameters with 100% coverage, including detailed descriptions for 'key', 'metadata', and 'ttl_seconds'. The description adds no parameter-specific information beyond the schema, so the baseline score of 3 is appropriate.
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 phrase, 'Atomically check whether... and claim it if not', which precisely identifies the tool's function. It clearly distinguishes the tool from its siblings by focusing on idempotency claiming, a unique capability not shared by fetch_structured or request_capability.
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 states when to use the tool: 'Use it before performing a non-idempotent action' and gives concrete examples (payment, message, write). It also provides a when-not-to-use directive: 'Do not use it as a general data store or as a result cache.'
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch a public URL and return its content as JSON validated against the schema you pass. Use it when you need data from a page and cannot parse it reliably yourself. Do not use it for URLs requiring authentication or a session, for internal networks, or when you already have the content — extract it yourself in that case. extracted_by tells you where the answer came from: structured_data when the page already published it (JSON-LD, OpenGraph, or a JSON body — exact and free) or model when it had to be extracted from the text. If structured extraction is unavailable, the response carries degraded: true, data: null and the page text for you to parse: check degraded before reading data.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public http(s) URL. | |
| schema | Yes | JSON Schema of the object you want back. Missing fields come back as null. | |
| instructions | No | Optional. What exactly to look for if the page is ambiguous. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description fully owns behavioral disclosure. It explains extraction modes (`structured_data` vs `model`), the degraded mode with `degraded: true`, `data: null`, and fallback `text`, and how to handle missing structured extraction. This is rich, honest behavior documentation.
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 dense but every sentence earns its place: purpose, usage boundaries, extraction modes, and degraded handling. It is organized from high-level action to detailed response interpretation, making it scannable and appropriately sized for the behavioral complexity.
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 and no annotations, the description fully explains expected response fields (`extracted_by`, `degraded`, `data`, `text`) and instructs the agent to check `degraded` before reading `data`. It covers the core functionality, failure modes, and usage exclusions, making the tool fully comprehensible.
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 100% for all three parameters, so the baseline is 3. The description adds minimal context beyond the schema (e.g., 'validated against the schema' reinforces the schema's purpose) but does not meaningfully extend 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?
States clearly that it fetches a public URL and returns content as JSON validated against a provided schema. The verb 'Fetch' and resource 'URL' are specific, and the exclusion of auth/internal/known content differentiates it from potential alternatives.
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?
Provides explicit when-to-use ('when you need data from a page and cannot parse it reliably yourself') and when-not-to-use (auth, internal networks, already-have-content). It further instructs on interpreting `extracted_by` to know the extraction source, giving clear decision guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Record a specific need that none of the tools available to you can cover. Today it almost always answers that the capability is unavailable, and suggests alternatives only when they genuinely exist; its purpose is to measure what agents ask for and nobody serves. Use it when you are blocked by a missing capability — not for general questions, and not for anything you can work out by reasoning.
| Name | Required | Description | Default |
|---|---|---|---|
| need | Yes | What exactly you need, in one or two sentences. Do not include personal data. | |
| context | No | Optional. What you tried and why it did not work. | |
| deadline | No | Optional. ISO 8601. | |
| would_pay | No | Optional. Whether your policy allows paying to get this solved. Answer honestly: a false answer unlocks nothing and degrades the measurement. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does so well: it discloses that the tool 'almost always answers that the capability is unavailable,' that alternatives are suggested only when they genuinely exist, and that the underlying purpose is to measure unmet agent needs. This is significant behavioral context beyond the basic operation.
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 three sentences, front-loaded with the core action, and each sentence adds value: what it does, how it behaves, and when to use it. There is no filler or repetition of schema details.
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 no annotations and no output schema, the description covers purpose, behavior, and usage well. It explains the likely response ('almost always answers that the capability is unavailable') and the fallback behavior. It does not fully specify the response format, but for a simple request-logging tool the description is nearly 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 100%, so the baseline is 3. The description does not add parameter-level meaning beyond the schema; however, it frames the overall intent ('Record a specific need') which aligns with the 'need' parameter. No extra semantics are provided for context, deadline, or would_pay.
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 states a specific verb and resource: 'Record a specific need that none of the tools available to you can cover.' It clearly distinguishes this from other tools by framing it as a fallback for missing capabilities and explicitly says it is not for general questions or things solvable by reasoning.
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 explicit when-to-use guidance: 'Use it when you are blocked by a missing capability' and includes exclusions: 'not for general questions, and not for anything you can work out by reasoning.' It does not name specific alternative sibling tools, but the exclusions are clear enough for an agent to avoid misuse.
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.
check_and_claimfetch_structuredrequest_capabilityMachine-native capabilities with explicit contracts and machine-readable commerce.
Reliable async execution for agent tool calls: schema gating, retries, idempotency, audit trail.
Payment decisions, durable evidence, x402 resource discovery and live gateway status for AI agents.
One MCP URL for all your connectors — scoped writes, enforced constraints, and a full audit trail.
Add one secure layer between your agents and this server.