Agent Evidence API

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds value beyond that by committing to a minimal return surface ({status, service, version}) and asserting no secrets or infrastructure detail are exposed, which is useful trust context for an agent deciding whether to call it.

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, front-loaded with the primary purpose, then cost/arguments, then return surface. Every sentence carries information an agent can act on, 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?

There is no output schema, and the description compensates by naming the exact fields returned. For a zero-parameter, read-only health check, nothing an agent needs in order to call it correctly is missing.

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 tool takes zero parameters, so the baseline is 4. The description reinforces this with 'takes no arguments', leaving nothing ambiguous about the call signature.

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 gives a specific verb and resource: verify the Agent Evidence API MCP server is reachable and report the running service version. It is unambiguous and clearly separable from the unrelated siblings research_evidence and sample.

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 states the cost and argument profile ('free to call, takes no arguments or payment'), which tells the agent this is a safe preflight/connectivity check to run at any time. It stops short of an explicit 'use this before X' rule, so it is clear context rather than full when/when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the bar is lower, yet the description still adds rate-limit context ('capped per day'), pricing awareness (0.01 USDC), and the shape of the return (source URL, retrieval time, content hash). It does not say what happens when the daily cap is hit or how failures are surfaced, which keeps it below a 5.

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 compact sentences, front-loaded with what the tool does, then the limits, then the decision rule. No filler; each sentence carries distinct 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?

There is no output schema, but the description covers the return content (up to three cited excerpts plus URL, retrieval time, content hash), the daily cap, and the absence of a verdict. That is everything an agent needs to call it correctly and 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?

Schema coverage is 100% and the schema text already explains both fields, including that the paid tool accepts up to five URLs. The description restates the 'one question and one public URL' contract without adding format or constraint detail beyond the schema, so the baseline 3 applies.

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 ('give one question and one public URL', get 'up to three cited excerpts') and explicitly positions itself as the free preview of the paid tool. It names the sibling research_evidence and what that tool adds, so an agent can distinguish the two without opening either 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?

Gives an explicit selection rule: use this 'to judge whether the paid call is worth 0.01 USDC', and states that assessment/verdict belongs to research_evidence over up to five sources. When-to-use, when-not-to-use, and the alternative are all named.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (readOnly/openWorld/idempotent), it discloses the freshness model (fresh retrieval per request unless served from a bounded cache, per-source retrieval timestamps), the auth profile (no API key, no account) and the cost model ($0.01 USDC on Base via x402, no charge when nothing is retrieved). These are exactly the behavioral facts an agent cannot get from 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?

Front-loaded with purpose, then usage, then returns, then operational facts — a sensible ordering. It is slightly padded: 'Every excerpt returned is cited evidence tied to its source URL' largely restates 'structured, cited web evidence' from the first sentence.

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?

There is no output schema, and the description compensates by describing the return shape (source URLs, retrieval timestamps, excerpts, publisher/document metadata, and a supported/contradicted/mixed/inconclusive assessment). Combined with cost, cache and auth disclosure, an agent has everything needed to call and interpret 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 description coverage is 100%, so the schema already documents mode, urls, language, question and max_sources, including the v0.1.0 requirement of at least one URL. The description adds no parameter-level meaning (no syntax, defaults, or tradeoffs), so the baseline 3 applies.

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 opens with a concrete verb+resource: 'Fetch public web sources and return structured, cited web evidence for a question or claim.' That is specific enough to separate it from the unrelated siblings (health, sample) without ambiguity about what the tool produces.

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 enumerates clear use cases — source verification, claim verification, evidence extraction, source-grounded research, comparing sources — which tells an agent when this tool fits. It stops short of naming when NOT to use it or any alternative, so it is clear context without exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover readOnly, idempotent and closed-world behavior, so the bar is lower; the description still adds the key non-annotated fact that it is free and enumerates the returned payload (verdict, per-source URL, retrieval time, content hash, cited excerpts). With no output schema, this return-content disclosure is genuinely valuable, though "always returns the same package" mostly restates idempotentHint.

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 tight sentences, front-loaded with purpose, then return contents, then the routing alternative. No filler and nothing the agent needs is buried.

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 no-arg sample tool with no output schema, the description supplies everything needed: what it returns, that it costs nothing and is deterministic, and which sibling to use for real queries. Annotations cover the safety profile, so no gaps remain.

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?

Zero parameters, so the baseline is 4. The description reinforces this with "Takes no arguments," which correctly sets the expectation that nothing needs to be supplied.

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 ("Return one real, previously produced evidence package") and immediately distinguishes itself from the sibling research_evidence by characterizing the latter as answering your own question. An agent can tell these two apart without opening either 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?

Explicitly frames the use case: see what a paid call returns "before spending anything," and names the alternative (research_evidence) for real questions. What's missing is an outright "do not use this to answer your question" statement, but the routing intent is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.