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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior: credits reset on the 1st of each calendar month, usage past the limit is billed as overage, and the free tier consumes no credits — context an agent needs to interpret the numbers correctly.

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 sentences, front-loaded with the verb+resource, with each trailing clause (reset date, overage billing, free-tier exemption) carrying distinct semantic weight. 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, so the description must convey return contents — and it does, listing the four values returned. The billing-cycle and overage notes make the returned numbers interpretable; only the cross-tool relationship to get_usage_stats is left open.

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 introduces no parameter concepts and correctly needs none.

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?

Names the resource (EzVerify account info) and enumerates exactly what comes back: plan, credits used, credits remaining, monthly limit. It's clearly a read of account/credit state, but it never contrasts itself with the sibling get_usage_stats, which an agent could plausibly confuse with this.

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?

Usage is only implied — an agent infers 'call this to check plan or credit balance.' There is no explicit when-to-use/when-not, and no pointer telling the agent to prefer get_usage_stats for usage history versus this for balance.

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 establish that this is a read-only, closed-world operation. The description adds useful behavior beyond that by saying it returns progress and counts, provides full results when completed, and does not consume credits.

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 short sentences with no wasted language. The core purpose is front-loaded, followed by return behavior and cost 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 a simple one-parameter read-only status tool with an output schema absent, the description covers purpose, returned information, completion behavior, and cost. It could add explicit polling or expiration guidance, but nothing critical 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 100%, and the request_id parameter is already documented as the value returned by verify_emails_bulk. The description adds no additional parameter format or constraints beyond the schema, so the baseline 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 states a specific verb ('Check the status') and resource ('a bulk verification job'), clearly separating it from the single-email and account/usage sibling tools. It also identifies the returned object as progress, counts, and full results when completed.

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 phrase 'bulk verification job' and the schema's 'request_id returned by verify_emails_bulk' give clear context that this is used after starting a bulk job. It does not explicitly discuss polling cadence or when not to use it, but the usage context is clear.

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 readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds genuinely new behavior: the tool is free and does not consume credits, and bulk job credits and per-address results are deliberately omitted. It also lists the returned metrics, which matters given there is no output schema. It stops short of describing aggregation boundaries (account-wide vs key-level) or the lookback handling near day edges.

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 sentences, no filler: the first front-loads the capability and metrics, the second carries the scope exclusions and the free-of-charge fact. Every clause earns its place and the routing information arrives before the caveats.

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 compensates by listing the metrics returned, and it explains the tool's relationship to bulk jobs and the account info tool. An agent has enough to choose it, parameterize it, and interpret its output without follow-up.

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 single 'days' parameter already carries its default (30) and max (365). The description restates the N-days window concept but adds no format, boundary, or edge-case semantics beyond what the schema provides, so 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 (EzVerify request statistics) and enumerates exactly which metrics are returned: total requests, credits used, valid/invalid/risky/unknown counts, average processing time. It also delimits scope against get_account_info and the bulk-job tools, so an agent can distinguish it from every sibling without opening a 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 routes the agent to get_account_info when the goal is a month's credit total, and implicitly frames this tool as the lookback-window option ('last N days'). It doesn't state outright when not to use it, but the exclusion of bulk credit data and the free/no-credit note give the agent a clear decision signal.

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 readOnlyHint=false, openWorldHint=true and idempotentHint=false, and the description adds the reason behind the non-idempotency: every repeated check of the same address is charged again, and unknown results are free. That credit accounting is exactly the kind of context annotations cannot express. It does not cover latency, SMTP timeout behavior, or auth requirements, which a live SMTP probe would plausibly have.

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: purpose first, then the return payload, then billing. The dense field enumeration earns its length because there is no output schema, and nothing is repeated from the schema 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?

With no output schema, the description correctly substitutes by enumerating status values and flags, and it explains the credit model. The one meaningful gap is operational: a live SMTP/MX check is slow and can time out, and nothing tells the agent what to expect or how errors surface.

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?

One required parameter at 100% schema description coverage, so the schema already fully documents `email`. The description adds no format, normalization, or casing guidance beyond it, which is the expected baseline when the schema carries the burden.

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?

Opens with a specific verb+resource ("Verify a single email address") and the word "single" implicitly marks the boundary against the sibling verify_emails_bulk. The return-field list further pins down what the tool produces. It stops short of naming the bulk sibling explicitly, so the differentiation is inferred rather than stated.

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?

"Single email address" hints that bulk verification belongs to verify_emails_bulk, but no sentence says when to use this versus that tool. Prerequisites, batch alternatives, and failure contexts are left to inference.

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?

Goes well past the annotations, disclosing async behavior, the request_id return, credit cost (1 credit per definitive result), free unknown results, and duplicate-billing semantics. With annotations already covering readOnly/openWorld/idempotent hints, this adds substantial context; only rate limits or failure behavior are missing.

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 the action and cap, then the follow-up step, then cost. Dense and near-waste-free, though the parenthetical about billing is slightly nested.

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?

No output schema exists, yet the description explains that the return is a request_id and how to retrieve results, and it describes the webhook payload via the schema. Complete for correct invocation, with only edge-case/failure behavior unaddressed.

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 defines both parameters and the webhook payload shape. The description adds only the 1,000-address cap and duplicate-billing semantics, which are useful but modest against a schema that does the heavy lifting; the baseline 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?

States a specific verb ('Submit an async bulk email verification job'), the resource, and the scope (up to 1,000 emails per request). The word 'bulk' plus 'list' cleanly separates it from the single-address sibling verify_email.

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?

Clearly implies when to use it (bulk lists) and explicitly routes the follow-up step: 'poll with get_bulk_job_status'. It stops short of an explicit exclusion such as 'use verify_email for a single address', so the boundary with the single-verify sibling is inferred rather than stated.

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