MillionVerifier MCP by usefulapi

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 the cost-relevant fact that querying credits does not launch a verification job — meaningful context beyond the 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?

A single front-loaded sentence with no filler. Every word contributes: the resource (credits), the action (read remaining), and the non-side-effect guarantee.

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 zero-parameter, non-destructive read with no output schema, the description conveys what the return value is (remaining credits). It could briefly note the units or response form, but the essentials are present.

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 there is nothing for the description to disambiguate; the 4 baseline applies. The description correctly implies a parameterless read.

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+resource: reading remaining MillionVerifier credits. The phrase 'without starting verification' implicitly separates it from the verification siblings (verify_email, upload_file), though it doesn't name them explicitly.

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 clause 'without starting verification' implies this is a safe pre-flight balance check rather than a verification call, but no alternative tool is named and no explicit when-to-use trigger is given. Usage is inferable rather than stated.

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, non-destructive, openWorld, so safety is covered. The description adds genuine beyond-schema context: it works on failed/canceled jobs, it never mutates state, and callers should wait between polls (rate-limit hint). It omits auth requirements and pagination/response-shape detail, keeping it from 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?

Four short front-loaded sentences: purpose, negative scope, further negative scope, and a polling caveat. No filler, though the opening 'Read an existing bulk file's...' slightly duplicates the title.

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, so the description carries the burden of describing returns — and it does, at a useful level (status, progress, aggregate counts, no per-email results). Combined with the annotations, an agent can call and interpret it correctly; only ID provenance and auth are unstated.

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 0% — the file_id property has only a numeric pattern and no prose. The description names it as 'its file ID' and thereby confirms its meaning, but does not say where to obtain the ID (presumably from millionverifier_upload_file) or clarify the numeric-string format. Marginal compensation for the coverage gap.

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 ('Read') and a precisely scoped resource: an existing bulk file's verification status, progress and aggregate result counts, keyed by file ID. The 'aggregate result counts' phrasing and the exclusion of per-email results clearly separate it from millionverifier_verify_email and millionverifier_upload_file.

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 explicit when-to-use context ('Includes failed/canceled jobs') and explicit exclusions ('without starting, stopping or re-verifying anything', 'Does not download individual email results'). The 'Wait between polls' note is actionable polling guidance. It stops short of naming the sibling tool to use for per-email results, so routing for that case is only implied.

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 (readOnlyHint=false, idempotentHint=false, openWorldHint=true), the description discloses cost implications ('billable job and spend credits'), the guard parameter, the no-retry/no-poll contract, and the duplicate-job risk on timeout. These are the exact behaviors an agent needs to avoid charging credits twice.

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?

Every sentence carries distinct information: purpose, cost/confirmation, return value and next tool, retry behavior, and duplicate warning. The billable/confirm warning is front-loaded, which is where an agent needs it most.

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 states the return shape ('a file ID'), names the consuming tool, and covers the side effects and failure modes of a non-idempotent, credit-spending call. Nothing essential for correct invocation 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?

Schema description coverage is 0%, so the description must compensate. It does clarify the operational meaning of `confirm` (a spend gate) and the 1–1,000 email range, but `filename` is never mentioned and no format expectations for `emails` are added beyond the schema's pattern.

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 first sentence states a specific verb and resource ('Create and upload a CSV of 1–1,000 emails for bulk verification'), which clearly separates it from the sibling single-address tool millionverifier_verify_email and the status tool millionverifier_file_info. An agent can identify the operation 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?

It gives explicit preconditions ('requires confirm:true'), routes the agent forward ('Returns a file ID for millionverifier_file_info'), and warns against a specific wrong action ('A timed-out submission may still create a job; check the dashboard before repeating it'). It also states that no automatic retry or polling occurs, removing ambiguity about follow-up behavior.

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?

With annotations already declaring readOnlyHint=false and idempotentHint=false, the description adds substantial behavioral context: credit spend, the confirm gate, the 10-second timeout, the fact that the charged GET is never retried, and that unknown/catch-all results do not establish deliverability. This is exactly the kind of hidden operational detail an agent needs for a charged external API call.

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 action, followed by the cost/confirm requirement and then operational caveats. Every sentence provides distinct and useful information, with no redundant restatement of the title or annotations.

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 charged, non-idempotent external verification call with no output schema, the description covers the critical unknowns: cost, confirmation requirement, timeout, retry behavior, interpretation of uncertain results, and recovery if the response is lost. Nothing essential for correct invocation appears to be 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?

Schema description coverage is 0%, so the description must carry parameter meaning. It clearly explains the operational role of confirm:true, which is the non-obvious parameter. The email parameter is only described as 'one email', but its format and length constraints are fully specified in the schema.

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: 'Verify one email using MillionVerifier's real-time API.' The phrase 'one email' implicitly distinguishes it from the bulk file-oriented siblings like millionverifier_upload_file and millionverifier_file_info. An agent can identify both the action and its single-email scope 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?

It gives clear usage context: the tool can spend credits, requires confirm:true, and has a 10-second vendor timeout. It also warns what to do if the response is lost. It does not explicitly name the bulk alternative or state when not to use this tool, so it stops short of a full when/when-not/alternatives statement.

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