Lyre Leads

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

Goes well beyond the readOnly/idempotent annotations by disclosing that the call is FREE and exact, that results break down by enriched/has email/contact email/relevance-checked, and that a small result reflects account search history rather than total data available. It even warns against a specific misreporting failure mode, which is behavioral context annotations cannot express.

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-loads the two key selling points (FREE and exact), then scope, then usage, then a clearly flagged CRITICAL caveat. No redundant sentences; the length is justified by the false-inference risk the tool carries.

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 without an output schema, the description enumerates the returned breakdown (enriched, has an email, contact email, relevance-checked) and the interpretation of results. Combined with a fully covered 19-param schema, nothing an agent needs to call this 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?

Schema coverage is 100%, so the 19 filters are already documented, and the baseline would be 3. The description adds value by stating filters can be combined in any combination and demonstrating a compound filter ('saved roofers have no CRM and a verified email'), clarifying these act as conjunctive optional constraints.

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 (counts) and a tightly scoped resource (leads THIS ACCOUNT has already searched and saved), and immediately differentiates from the inventory reading by naming estimate_list as the tool for 'how many X do you have'. An agent can route correctly 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?

Gives explicit when-to-use ('size a job over data the account already owns before spending') with a concrete query example, plus two hard exclusions: it is NOT an inventory, and never report the number as available data. The alternative (estimate_list) is named for the excluded case.

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 cover write/destructive/idempotency, and the description adds real context beyond them: the token cost ratio (one token per five businesses), that it does not enroll the business, that email verification is included free, and that it runs asynchronously returning a job id. The three-state field contract is a useful honesty guarantee. It stops short of saying what re-enrichment overwrites when force is set.

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 core action and outcome, then cost, alternative, and async flow. The long middle enumeration of 50+ fields is informative but the longest sentence in the whole definition and could be trimmed without loss.

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, but the description compensates by explaining the return (a job id, polled via get_job_status) and the field-value contract. For a downstream write operation with rich annotations, nothing an agent needs to invoke 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?

Schema coverage is 100%, so both parameters are already documented in the schema itself (force and result_ids both have descriptions). The description adds no syntax or semantics beyond that, which is the expected baseline when the schema carries the load.

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?

Specific verb+resource ('Fetch each lead's website and extract 50+ fields') with a concrete enumeration of what it extracts. It also explicitly distinguishes itself from enroll_leads and verify_emails, so an agent can route correctly without opening schemas.

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 the alternative and the condition that selects it: 'To keep businesses current, use enroll_leads instead.' It also states the follow-up flow ('returns a job id, poll it with get_job_status') and the cost model, leaving nothing 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 beyond the annotations by disclosing recurring monthly re-checks for the lead's lifetime, the cost model (one token per two businesses, paid once), free/skipped cases, and that it runs asynchronously returning a job id to poll. These are exactly the traits an agent needs before spending the user's tokens, none of which the hints convey.

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-loads the action and its effect, then layers cost, skip rules, usage guidance, and the async follow-up in a logical order. Slightly long for a one-parameter tool, with small redundancies ("for free" / "at no cost"), but nearly every sentence carries decision-relevant 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?

No output schema exists, yet the description explains the return value (a job id) and the exact next call (get_job_status with kind "enrich"). Combined with cost, skip, and recurrence semantics, an agent has everything needed to invoke and follow up 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% and there is a single parameter, so the baseline is 3. The description adds real meaning by constraining which lead ids are meaningful to pass (imported or chosen leads the user cares about) and noting that some ids are skipped at no cost, which the schema's "Lead ids to enroll" does not say.

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 precise verb+resource (enroll leads) and immediately expands what enrollment means: enrich now plus monthly re-checking with change signals. This behaviorally separates it from a one-off enrichment tool, but it never names the sibling (enrich_leads) it differs from, so an agent must infer the boundary.

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 it for the imported or chosen leads the user cares about most") and clear exclusions (search-found businesses already enrolled; already-enrolled leads and leads without a website are skipped), plus the required follow-up action via get_job_status. It stops short of contrasting with the one-off enrich_leads alternative.

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 only cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description goes well beyond by disclosing that it is free and needs no account, that covered areas are skipped, and that exact cost is impossible because billing is 1 token per newly discovered business. That billing and skip model is exactly the context annotations cannot carry.

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-loads the key qualifier ('FREE, no account needed') and keeps to three sentences. The final sentence explaining the cost ceiling is long and slightly conversational, but every sentence carries information an agent needs.

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 describing what comes back: a count of grid points plus already-covered areas. Combined with the explicit cost caveat, an agent has enough to call this correctly, though it never states the response shape or whether estimates are cached.

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 all four parameters, including the grid/city enum, are fully documented. The description hints at the 'grid points' concept but adds no syntax, defaults, or format detail beyond what the schema already supplies, so the baseline of 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 ('Size') and resource ('a search_areas run') and immediately clarifies the two things it quantifies: grid points and already-covered areas. An agent can distinguish it from the sibling search_areas (which executes the run) 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?

'Size a search_areas run before starting it' gives clear timing relative to the execution tool, and the note about skippable covered areas tells the agent why this matters. It does not name estimate_list, the sibling that sizes list-based searches, so the routing between the two estimate tools is 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?

Adds substantial context beyond the annotations: it is free and needs no account, returns exact token costs by stage, reports account balance and affordable maximum, and enumerates the data points per lead. Cost mechanics (1 token per lead, 2 tokens per verified contact) are disclosed nowhere else and are essential for interpreting the estimate.

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-loads the key qualifier ("FREE, no account needed") and keeps every clause meaningful, but the embedded quoted question and the long trailing justification about count_saved_leads make it denser than necessary.

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 burden of explaining returns and does so: cost broken down by stage, balance, affordable maximum, and per-lead data points. Combined with full schema coverage and read-only annotations, 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 baseline is 3, but the description adds pricing meaning to both parameters by tying lead_count to one-token-per-lead and include_contacts to two-tokens-per-person. It stops short of naming the parameters explicitly, so it enriches rather than fully documents them.

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 (estimate/price a list of N businesses) and precisely frames the question it answers. It also explicitly distinguishes itself from the sibling count_saved_leads, so an agent can route correctly without inspecting 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?

Explicit when-to-use ("THIS is the tool to use when a user asks what Lyre Leads can get them") and explicit when-NOT-to-use with the named alternative ("Do NOT use count_saved_leads for that question") plus the reason: leads are generated on demand, not stored. Nothing is 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?

Annotations already cover readOnly, idempotent, non-destructive and non-open-world, so the safety profile is established. The description adds context annotations cannot carry: it is free and requires no account, and results are returned most-populous-first with an id per area, which is behavioral/return detail absent from structured 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?

Four tight sentences with no filler. The most decision-relevant fact (free, no account needed) is front-loaded, followed by the call patterns and the disambiguation rule.

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 compensates by describing the return shape (areas ordered by population, each with an id) and the downstream use of that id. Together with annotations and the fully documented schema, nothing needed to call this 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?

Schema description coverage is 100%, which sets a baseline of 3. The description goes beyond the schema by explaining the interaction of parameters: no q means browse, no country means the country list, and the returned id is the value to hand to search_areas for ambiguous names.

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 ("Look up the areas search_areas accepts in a country") and explicitly ties itself to the sibling tool search_areas, so an agent can distinguish the discovery step from the search step. It also defines scope (per-country) and output ordering up front.

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 call patterns: omit q to browse, omit country to list countries, and pass a specific id when a place name is ambiguous (four Houstons, thirteen Springfields). That is concrete when-to-do-what guidance. It does not mention sibling alternatives such as estimate_area_search for sizing an area, so it stops short of full routing.

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 destructive/openWorld/non-idempotent, but the description adds behavior annotations cannot express: the exact cost model (2 tokens per person, up-front reservation of 2 tokens per lead id, settle on delivery), the async job-id + get_job_status polling contract, and a full outcome vocabulary (verified/published/catch_all/searched) with what each means.

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 triggering condition, then cost, then sibling differentiation, then return/polling behavior. Dense and mostly waste-free, though the cost/reservation sentences are slightly circuitous and could be tightened without losing meaning.

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 expensive, mutation-like, open-world tool with no output schema, the description supplies everything needed: eligibility, cost ceiling, async polling path, and the meaning of each possible per-lead outcome. Nothing an agent needs 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?

There is only one parameter and schema coverage is 100%, so the schema already documents result_ids including the eligibility and skip-without-charge rule. The description's added value here is limited to tying cost to 'per lead id sent', which is marginal on top of the schema. Baseline 3 for a fully-covered single parameter.

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 chain: search the open web for named people (owner/founder/director), then resolve and verify their email in one run. It explicitly contrasts itself with 'enrichment', so an agent can route correctly without inspecting 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?

Prequalifies the audience precisely: 'for leads with a website but no named contact', and names the alternative (enrichment) along with the condition that selects it (people listed on the business's own site, already free). It also flags the case this uniquely reaches that enrichment cannot.

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 (readOnlyHint, idempotentHint, destructiveHint=false), so the description correctly adds non-obvious context instead: the token pricing model, rollover policy (up to three months' allowance), and the fact that the purchase link is returned rather than any action taking place. That genuinely helps interpret the balance number.

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 purpose is front-loaded in the first sentence, followed by the token economics needed to make the returned number meaningful. The middle pricing sentences are dense and arguably belong to the consuming tools, but they are not padding and the final sentence cleanly closes the out-of-scope boundary.

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 parameters and no output schema, the description carries the burden of explaining what comes back: a token balance, plan info, and a purchase link. It covers all of that and adds the rollover rule, leaving only minor gaps such as the exact result shape.

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 per the rubric the baseline is 4. There are no arguments to misinterpret, and the description sensibly spends its words on output meaning instead of phantom parameters.

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 opening sentence states a specific verb and resource: retrieve the account's token balance and plan. It is immediately clear what the tool returns, though it never names the sibling tools whose token consumption it contextualizes (search_leads, enrich_leads, etc.), so it is clear but not sibling-differentiating in an explicit way.

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 one exclusion clearly -- plans are bought and changed on the website, not through these tools, and the result carries the link. However, it never says when an agent should call this tool (e.g., before spending tokens on search/enrich operations), leaving the primary usage trigger 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?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuine context beyond that: jobs are expected to be long-running ('a grid search works through many map points, and enrichment fetches every website in the batch'), which tells the agent not to treat slowness as failure. It stops short of describing terminal states, failure modes, or progress reporting.

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 with zero filler: the set of originating tools is front-loaded, the call mechanics follow, and the long-duration caveat closes. Every sentence earns its place.

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 polling tool with no output schema, the description never says what the returned status looks like or, critically, that completed results are retrieved via siblings like get_search_results or list_results. The kind enum and the long-job expectation are well covered, but the post-completion path 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 enum's own description already maps each kind to its originating tool, including enroll_leads under "enrich". The description's "pass the job id and its kind" and the tool-to-kind mapping largely restate the schema, adding only marginal emphasis. 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?

States a specific verb (poll) and resource (background job) and names exactly which sibling tools create the jobs it polls (search_areas, enrich_leads, enroll_leads, find_contacts, verify_emails). An agent can distinguish this from result-fetching siblings like get_search_results 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?

Clearly establishes the usage context: call this after one of the named tools starts a background job, passing its job id and kind. It does not, however, say when to stop polling or route the agent onward to result tools (get_search_results, list_results) once the job completes, nor mention polling cadence.

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 safety (readOnly, idempotent, non-destructive), and the description adds real behavioral context on top: it is free, paginated at 100, compact-by-default with a 'full' escape hatch, and the summary reflects the whole search population rather than the page. The note that enrichment continues after the search finishes and requires a re-read is exactly the kind of non-obvious behavior an agent cannot get from structured 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?

Dense but front-loaded: cost, scope, filters, return shape, summary semantics, and enrichment caveat all in one compact block with no filler sentences. It is longer than typical, but each clause carries decision-relevant 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 5-parameter tool with a nested filters object and no output schema, the description compensates well: it describes what each lead contains, the difference between compact and full, and how summary counts are scoped. An agent has everything needed to call it 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%, so the baseline is 3, but the description goes further: it shows concrete filter keys (hasVerifiedEmail, noFBPixel) not present in the schema example, clarifies that 'full' returns every database field, and explains what the summary counts. Only the page/limit semantics are left entirely to 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?

States a specific verb and resource ('Read the leads a search_areas job found') and ties the tool to the exact producing sibling, so an agent knows this reads results of a specific job rather than doing the searching itself. Scope ('up to 100 per page') is stated up front.

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 clear operational guidance: read further pages only when the user asks to see more leads, and re-read while enrichment is still landing. It does not, however, explicitly contrast this tool with siblings like list_results or search_leads, so the routing decision relies on 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?

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so the safety profile is covered. Beyond that the description adds real behavioral context: the call is 'FREE', wait_seconds blocks up to 45 seconds for in-flight enrichment, and the summary with a search_id counts the whole search rather than just the returned page.

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 cost flag 'FREE.' and the core purpose are front-loaded before the field list, and no sentence is pure filler. The middle sentences run long and pack return-field enumerations densely, which slightly hurts scannability but not information value.

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 carry return-value burden and it largely does: it describes the compact view, the summary/next-steps payload, and how detail='full' changes output. Pagination behavior and the exact shape of the summary are left implicit, but nothing critical 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%, so every parameter is already documented at the schema level. The description mostly restates that coverage (search_id from search_leads, wait_seconds up to 45, detail 'full') without adding much new meaning, so the baseline of 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 specific verb and resource ('Read saved leads') and then enumerates exactly which fields come back (email and verification state, contact, relevance verdict with site sentence, software, technologies, signals). It also distinguishes itself from search_leads by requiring that tool's search_id, so an agent can tell it apart from siblings like get_search_results or count_saved_leads.

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 operational guidance: 'Pass the search_id from search_leads to read that search' and 'omit for all results', plus the wait_seconds timing tip. It does not explicitly rate itself against alternatives such as get_search_results or count_saved_leads, so the routing guidance is strong but not exhaustive.

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 cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds substantial behavior: nothing saved or enriched, no emails/contacts/software returned, phones partly hidden, 20-result cap, and that no sign-in is started. This is exactly the extra context the annotations cannot carry.

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 key constraint (free sample, nothing saved) and then the routing rule. It is longer than average but nearly every clause carries operational information; the sibling comparison sentence is dense but earns its length.

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 describes both the shape and limits of the return (first page, up to 20, phones partly hidden, no emails/contacts) and the account/auth implications. Nothing needed 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?

Schema coverage is 100%, so baseline is 3, but the description adds meaning beyond the schema: accepted place formats and the ambiguous-shared-name behavior (picks the largest, lists the others). It does not clarify the optional country parameter's interaction further.

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 with scope: the first page (up to 20) of ONE Google Maps search for a kind of business in a place, phones partly hidden, nothing saved. It explicitly distinguishes itself from search_leads and search_areas by naming both siblings and their differing behavior.

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 conditions (user asks for a preview/sample, or no account connected) and when-not (search/find/pull/list businesses), with the reason: the siblings save and enrich and may trigger sign-in. The agent can route correctly without 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?

Adds substantial behavior beyond the annotations: billing is 1 token per NEW business with existing listings free plus a small per-page minimum, results are auto-enriched, relevance-checked, address-verified, and enrolled in monthly re-checks, and concurrency is limited to two searches. It also discloses the ambiguous-area failure mode and the polling handoff to get_job_status/get_search_results, which the destructive/openWorld annotations alone would not convey.

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 behavior lead, with operational details (cost, polling, disambiguation, concurrency) following in a dense but ordered block. Several sentences are long and pack multiple clauses, so it is efficient without being maximally tight.

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 correctly supplies the return contract (job_id, poll get_job_status with kind 'search', then read with get_search_results). Combined with the cost model, concurrency limit, and disambiguation behavior, an agent has everything needed to invoke and follow up 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 real parameter meaning: the mode tradeoff (grid vs paging from a centre) is quantified with cost/exhaustiveness evidence, and the areas parameter's ambiguity handling (returns candidate ids, starts nothing, requires resend with an id) is documented nowhere else.

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 a specific verb+resource (area search that sweeps a grid of map points live against Google Maps as a background job) and ties it to a concrete outcome (1,061 roofing contractors in Houston vs 255 from paging one centre). The scope and the contrast with centre-paging make it distinct from siblings like search_leads, preview_search, and estimate_area_search.

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 clear usage context: it is 'the search to use for coverage,' runs as a background job requiring a poll loop, and is capped at two concurrent searches per account. It also tells the agent what to do on an ambiguous area name (ask the user and resend with the id). It never explicitly names when NOT to use it or which sibling (search_leads, preview_search, estimate_area_search) to prefer instead.

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?

Despite annotations (destructiveHint true, readOnly false, openWorld true), the description discloses the token cost model, that existing leads are free, the background enrichment (~2 min for 20) with its outputs, and the return shape (Maps listing + search_id). This is rich 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?

Front-loads the core action and scope in the first sentence, then alternatives, cost, enrichment, and next steps. It is dense but every sentence carries actionable info; slightly long but not padded.

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, but the description explains return values (Maps listing, search_id), the enrichment payload, cost implications, and the required follow-up call. An agent can invoke correctly and know what to do next.

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 schema carries parameter syntax. The description still adds meaning: pages are 'about 20 per page' and the query is a 'city centre' scoped search, reinforcing the pages and scope semantics. Marginal extra value, so a 4.

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 (Search) and resource (ONE city / businesses) and the scope (city centre, 1-5 pages). It explicitly distinguishes itself from search_areas, naming the sibling and the volume difference.

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 ('quick search, a page of results or one town') and when-to-use-otherwise ('for a whole city or several, use search_areas'), plus the follow-up call list_results with its wait_seconds. Nothing is 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?

Despite annotations covering the safety profile, the description adds substantial context beyond them: cost ('included in every plan at no charge'), caching ('a re-check within 90 days reuses the cached verdict'), async execution model, the polling contract, and the semantic meaning of all four verdict states. The explicit 'Never treat catch_all as verified' warning is exactly the kind of behavioral nuance annotations cannot express.

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 clause carries load — cost, caching, execution model, polling instructions, and state semantics — with no redundancy. The async contract is front-loaded before the state definitions, giving a natural reading order.

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 fully compensates by explaining the return value (a job id), the polling path, and the four possible verdict states plus the catch_all caveat. An agent can complete the call and interpret results without any missing information.

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 parameter's max of 2,000 is already documented in the schema, so the description adds no syntax or format detail beyond it. Per the high-coverage baseline, a 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 and resource — 'SMTP-verify the business emails on saved leads' — and names the provider (MillionVerifier), which cleanly separates it from siblings like enrich_leads or find_contacts. An agent knows exactly what operation this performs 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?

Gives clear operational context: it runs in the background, returns a job id, and must be polled via get_job_status with kind "verify" until completed. It does not, however, state when to prefer this over alternatives such as enrich_leads, so it falls short of full when/when-not routing.

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