VeritaHire Hiring Intelligence

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

Annotations only declare read-only and closed-world; the description adds genuinely new behavior: the 'building' status with retry_after_seconds for un-analysed postings, and a 'not_held' status with fallback market_now and a report link. With no output schema, these response-state disclosures carry real weight, though expiry/freshness of cached results is unstated.

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?

Roughly the first two lines are an occupation catalogue ('healthcare, finance, IT, engineering... retail and food') that does no work for tool selection and delays the actual point. The remaining content is dense but run-on, with multiple ideas packed into single sentences.

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 six-parameter, no-output-schema tool it covers the essentials: how to identify the posting, what comes back for free, what the paid sibling adds, and the two degraded response statuses. What's missing is handling of the zero-required-parameter case and precedence among identification inputs.

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 50% (city, title, employer undocumented), but the description compensates by spelling out the three identification paths — careers-site URL, VeritaHire job id, or employer+title+city/state — which is meaning the schema alone doesn't convey. It stops short of saying which combination takes precedence when several are 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?

The description states a concrete resource (the posted pay range for a role within 25 miles, employer count) and distinguishes itself from the named sibling request_competitive_hiring_report, which holds the competitor-by-name detail. The core purpose is clear, though it is buried behind a 20-occupation enumeration that obscures the verb.

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 explicitly partitions free data (pay range, employer count, time to close) from what requires the request_competitive_hiring_report call, which is a real when-to-use/when-to-use-the-other statement. It gives no guidance for choosing against hiring_market, hiring_signals, or is_job_still_open, so the routing is only partial.

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 readOnly/destructive annotations, it discloses real behavioral traits: data comes from employers' own careers sites, is rebuilt daily, is free, and no employer is named in the output. Missing pagination or result-volume expectations, but the provenance and freshness disclosure is meaningful added context.

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 and information-dense, but the first sentence is an unwieldy run-on that re-enumerates fourteen job categories already listed in the occupation parameter description. That duplication is waste in an otherwise tight definition.

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 carries the return-value explanation and does so adequately by naming the fields returned (postings, employers hiring, pay range, employment type). It could be slightly more explicit about result granularity or volume, but an agent can call it 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?

Schema coverage is 100%, so the baseline is 3, but the description adds practical value with concrete occupation phrasing examples ("registered nurse", "truck driver", "warehouse") and confirms state accepts a code, a name, or the US default. That reduces format ambiguity the schema leaves open.

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 resource and scope: live postings, employers hiring, posted pay range and employment type for one occupation, nationally or in one state. It distinguishes itself from request_competitive_hiring_report, but sibling tools like hiring_signals and job_openings_index sound overlapping and are never differentiated.

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 (one occupation, national or single state, plain-word occupation phrasing) and explicitly routes the agent to request_competitive_hiring_report when per-employer detail, time-to-close, or requirements are needed. It offers no guidance on when hiring_signals or job_openings_index would be the better choice.

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/openWorld=false, so safety is covered; the description adds real substance on top: the exact thresholds used (3x usual time-to-close, 30-day repost window), that examples are named and filtered on stated pay topping $60K, and the free-tier boundary against the paid row-level API. It omits any mention of rate limits, auth, or coverage/lag of the underlying careers-site crawl.

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 and free of filler, but the first sentence is a long clause-heavy run-on ("how many live roles have been open at least 3x longer than that same employer usually takes to close a role (stuck)") that takes effort to parse. Little waste, but the structure could be broken up without losing 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?

For a 3-parameter read tool with no output schema and annotations covering the safety profile, the description covers source, metrics, thresholds, filtering scope, and the free-vs-paid split well. Gaps are secondary: no indication of data recency, result size, or what fields the named examples carry.

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 does add one genuine constraint the schema does not state: results are "nationally or for one state and one industry," implying a single state and single industry per call rather than a list. The min_pay filter and the $60K example-pay floor are related but the description does not clarify how they interact.

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 resource and metric pair: counts of roles open 3x longer than the employer's usual close time (stuck) and roles reposted in the last 30 days, sourced from employers' careers sites. An agent can tell this is a labor-market signal tool, not a job search. It never differentiates itself from siblings like hiring_market or job_openings_index, so the boundary is only implied by the metric definitions.

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?

Names an audience ("recruiter or staffing firm") and implies a use case (finding roles that aren't filling), and states that free counts/examples are returned while the row-level list comes from the separate Hiring Signals API. It gives no explicit when-to-use versus hiring_market, job_openings_index, or compare_job_posting, and no 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 the safety profile (readOnly, non-destructive), so the bar is lower, and the description still adds real context: the re-read mechanism, an ~36-hour lag before a posting is marked closed, a three-state result including 'unknown', and a last-confirmed timestamp. What is missing is any note on rate limits or caching.

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, both earning their place: the first front-loads the answer and its caveats, the second states applicability. No filler or restated 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 return-value burden and does: the tri-state result, the last-confirmed timestamp, and the ~36-hour freshness window. Together with annotations, an agent has enough 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 coverage is 50%: url is documented, job_id is not. The description partially compensates by framing the input as a 'careers-site link', which clarifies the url parameter's expected form. It says nothing about job_id or how the two parameters relate, so the gap is only partly filled.

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 question/verb-resource: whether a job posting is still open on the employer's careers site, and returns one of three named states. It is clearly distinguishable from siblings like compare_job_posting and hiring_market without opening any 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?

The description gives an input precondition ('given its careers-site link') and notes it works for any employer's posting, which implies when it applies. But it never states when to prefer this over compare_job_posting or the report tools, nor any exclusions (e.g., non-careers-site links).

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 readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuinely useful context the annotations cannot carry: the source (employers' careers sites), the next-morning publication lag, and free CC BY 4.0 licensing. It says nothing about caching, rate limits, or what an empty/short series looks like, so it is solid but not rich.

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?

One dense sentence, front-loaded with the producer and resource name, with the enumerated outputs following in a logical order. The long comma list of metrics is heavy but every clause identifies a distinct returned value, so little is wasted.

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 present, the description carries the return-value burden and does so by enumerating the metrics and noting the JOLTS comparison month and the daily series. An agent can predict the response shape well enough; only response nesting, units, and the effect of `days` on the series length remain unspecified.

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 single `days` parameter (1-120, default 30) is fully documented in the schema. The description only alludes to 'the daily series' without adding format or default behavior, so it neither compensates nor detracts — baseline 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 names a specific resource — a daily index of open US job postings built from employers' own careers sites — and lists the values it exposes (index level, 7-day average, changes, churn shares, JOLTS comparison, series). It is clearly distinguishable from the job-search siblings like search_live_jobs or get_job, though it reads as a data catalog entry rather than an explicit 'returns X' verb statement.

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?

There is no statement of when to call this versus alternatives; an agent gets no cue that this is macro/labor-market context while search_live_jobs is per-posting. No prerequisites, no exclusions, no mention of how the days window should be chosen relative to the audience.

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 read-only, non-destructive, non-open-world behavior, but the description adds genuinely useful operational context: no email is sent by the tool, no email address is accepted, and VeritaHire only mails the address the manager types on the site. It also discloses that the first report is free. It does not describe link lifetime, failure modes, or rate limits.

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 action and the 'no email' clarification are front-loaded, and the planned-role fallback is placed last where it belongs. The middle enumeration of report contents (pay changes, what more applicants cost) is verbose and reads partly promotional, but each sentence still carries usable selection 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 an 8-parameter, 0-required tool whose result is a link, the description covers both invocation modes, the free-tier fact, and the human hand-off. What remains uncovered is minor: how the link is returned, whether it expires, and why city/state and location coexist for a posted role.

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 only 25% (pay and location only), so the description must compensate, and it does the most important part: it explains the two mutually exclusive parameter groupings (posting identity via job_url/job_id/employer/city/state versus planned-role via title + location + pay). It leaves individual params like employer and city/state uninterpreted, so it doesn't fully close 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?

The description states a specific verb and resource: it returns a *link* for the hiring manager to open, and it explicitly corrects the likely misreading that this tool emails a report. The report's scope is spelled out (same-role employers within 25 miles, their pay, close speed). It does not name or contrast itself against the siblings (compare_job_posting, hiring_market, is_job_still_open), so it stops short of a 5.

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 when-to-use branches: a role already posted (pass a posting) versus a role the employer is PLANNING to post, where you pass title + location (+ pay) instead. It even covers the edge case of a posting VeritaHire does not hold. It never routes the agent away to a sibling tool, so no explicit 'use X instead' guidance.

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