Email Verifier

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

Annotations already declare read-only, idempotent, non-destructive behavior, and the description adds substantial context: what checks are performed, possible status values, score range, confidence/source fields, warnings, disclaimer, and address non-logging. This is well beyond what the annotations provide.

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 checks and use case, and it is generally dense rather than chatty. The lengthy enumeration of response fields is partly redundant because an output schema exists, which keeps it from being maximally concise.

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 one-parameter read-only lookup with an output schema and safety annotations, the description provides enough context to invoke it correctly: use cases, checks, status semantics, confidence/source metadata, warnings, and privacy behavior.

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 schema explains that a full address is accepted with only the domain part used. The description adds an example domain but no additional format or validation semantics, so baseline 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 specific domain-level checks (mail acceptance, MX hosts, disposable/free-mail status, SPF/DMARC) and the intended decision context. Its domain scope clearly differentiates it from sibling tools like verify_email and verify_emails, which operate on individual addresses.

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 contexts: before trusting a sender domain or when onboarding a company. However, it does not explicitly name alternatives or state when not to use it, such as routing single-address checks to verify_email.

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, idempotentHint and destructiveHint=false, so safety is covered; the description usefully adds the privacy guarantee ('No logging of addresses') and the dedupe default. However, the response sketch lists verification-style fields (status deliverable|risky|undeliverable, reason, score 0-100, checks run) that read like verify_emails output and are not obviously what an extraction call returns, which risks misleading the agent.

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?

Purpose and scope are front-loaded in the first clause, and the remaining sentences are short, high-density fragments rather than prose padding. Every element (free, pair-with, privacy) carries 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?

An output schema exists, so enumerating result/status/score/data_confidence/warnings/disclaimer duplicates structured data and consumes most of the description — and the enumerations look copied from the verification tools, so the agent may expect fields this tool does not return. Core extraction behavior, dedupe, and privacy are covered, leaving the response claim as the gap.

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 schema documents 'text' but leaves 'dedupe' with an empty description; the phrase 'deduped by default' fills that gap and tells the agent what the flag controls. Neither param needs format syntax beyond 'any text/HTML'.

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 ('Find every address in a block of text or HTML') plus a scope detail (deduped by default). This is clearly distinguishable from verify_email/verify_emails, which check addresses rather than extract them.

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?

'Pair with verify_emails' gives an explicit downstream workflow, and 'Free.' signals cost constraints. It does not state when NOT to use it or how it differs from domain_check, but the extraction-vs-verification split is inferable from the first sentence.

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, non-destructive and closed-world, so the bar is lower, but the description still adds genuinely new context: the call is free, addresses are not logged, and the suggestion may be null. The long enumeration of response fields is mostly duplicated by the output schema, but the privacy and null-result disclosures are real value.

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 useful content leads — what it fixes, example, null semantics — but the trailing list of response fields (status, reason, score, data_confidence, estimated_items, sources, data_version, warnings, disclaimer) is largely redundant given an output schema exists. Structurally sound; somewhat padded at the end.

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 an output schema present, return values need not be spelled out, and the description covers purpose, example input, cost and privacy. The one real gap is the relationship to verify_email, since this tool also returns deliverable/risky/undeliverable statuses, leaving overlap unexplained.

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?

There is a single parameter with 0% schema description coverage, so the description carries the burden. It supplies a concrete example ('sara@gmial.con') and hints that stray spaces and dots are tolerated in input, but it never states the format constraints or what counts as a malformed address — partial compensation only.

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 ('fix common typos' in email addresses) and anchors it with concrete typo examples (gmial.com, hotmail.con, stray spaces/dots). The core action is unambiguous, but it never names or contrasts the obvious sibling verify_email, which also returns a deliverability status, so an agent cannot tell them apart from the description alone.

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 by 'Fix common typos' and the example input; there is no statement of when to prefer this over verify_email or verify_emails, and no note on what to do when the suggestion is null. An agent must infer the calling condition.

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?

Adds real traits beyond the annotations: 'No logging of addresses' (privacy), SMTP probe is 'Slower (1–8 s); some servers block it', and catch-all detection affects result meaning. Slight tension with openWorldHint=false, since DNS/MX lookups and SMTP RCPT probes reach external servers, though this is a labeling nuance rather than a direct contradiction.

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 one-line purpose, then checks, then an example, then the response shape — a sensible scanning order. It is dense but every clause names a distinct capability an agent would otherwise have to discover by trial.

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 three simple params, a full schema and an output schema, the definition covers inputs, cost implications and return semantics well. The only real hole is routing guidance versus the four sibling tools, which the description never addresses.

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 schema already explains smtp_check's handshake, latency and blocking. The description only echoes these as 'optional SMTP RCPT probe with catch-all detection and optional SPF/DMARC' and adds no format, cost or edge-case detail the schema lacks.

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+scope: 'Full check of one address', where 'one' implicitly separates it from the batch sibling verify_emails. The enumerated check list (syntax, MX, disposable, role, typo, SMTP, SPF/DMARC) makes the tool's remit unmistakable against domain_check, extract_emails and suggest_fix.

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 implied rather than stated: the worked example ('john.doe@gmail.com', smtp_check false) shows a typical default call, and 'optional' flags hint at the cheap-vs-deep tradeoff. However, it never says when to pick verify_email over verify_emails, domain_check or suggest_fix, nor when a caller should skip the tool.

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, idempotent, non-destructive), the description discloses parallel execution, per-domain DNS caching, per-unique-address billing, and 'No logging of addresses' — privacy and cost facts not derivable from structured fields. It also enumerates the status values and result fields.

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 and the sibling equivalence, then cost, then example, then response shape and privacy note. Dense but every clause carries new information; 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?

Even though an output schema exists, the description usefully previews the status enum, score range, and confidence fields, and covers cost, privacy, and performance expectations. Nothing material 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 coverage is 100%, so the baseline is 3; the description adds meaning by tying dedupe to billing ('charged per unique address') and showing an example call with smtp_check false. It does not explain check_policy or the performance tradeoff of smtp_check beyond what the schema already says.

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 (verify) and resource (a list of emails), explicitly frames it as the batch counterpart to verify_email, and summarizes the return shape. An agent can distinguish it from the singular sibling 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?

'Same checks as verify_email for a list' gives clear context that this is the multi-address variant, and the example plus 'Charged per unique address' signals cost-sensitive bulk use. It stops short of explicit when-not guidance or naming a threshold at which verify_email should be preferred instead.

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