Digital Business Portal

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

With zero annotations, the description carries the full load and does it well: it discloses robots.txt compliance with a named user agent (DBP-Reader), a hard token range with default, and a free-tier rate limit of 10 pages/day. It stops short of failure-mode behavior — timeouts, JS-rendered pages, or what is returned when robots.txt disallows the fetch.

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 short sentences, front-loaded with the core action and output shape, followed by compliance, parameter bounds, and quota. Every sentence carries distinct information and nothing is repeated from the schema.

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 2-parameter read tool with no annotations and no output schema, the description covers action, return format, compliance, parameter bounds, and quota — enough for an agent to invoke it correctly. Minor gaps remain around error and non-HTML content handling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate and largely does: it supplies the max_tokens range 50-4000 and the 2000 default, neither of which appears in the schema beyond the bare default value. The url parameter is only constrained indirectly via 'one public web page', leaving the accepted scheme/format unspecified, which keeps this below a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Read) and resource (one public web page) and names the return payload (Markdown plus title and metadata). The sibling tools are all verification/lookup utilities, so the fetch-and-extract scope is unambiguous without needing a named alternative.

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 word 'public' plus the robots.txt note implicitly excludes private, authenticated, or blocked pages, and the '10 pages per day' limit tells the agent this is a scarcity budget, not a bulk crawler. However, it never states positively when to choose this tool over another, nor what to do when a page is blocked or the quota is exhausted.

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

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

With no annotations, the description carries the full burden and does substantial work: it discloses that matching is deterministic keyword matching with no AI, and that requests are logged for 30 days after best-effort scrubbing. Those are exactly the privacy and mechanism facts an agent needs before sending user text. It omits failure behavior when nothing matches and any latency expectations, keeping it below a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence delivers the input instruction first, then the return, then the privacy caveat. No filler or redundancy. The privacy clause is dense but relevant enough to keep; the sentence is slightly overloaded with parenthetical details.

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 2-parameter discovery tool with no output schema and no annotations, the description covers input format, matching mechanism, and data handling. The notable gap is return-value shape — what a match response looks like and what happens on no match — but the core of what an agent needs to call it correctly is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate, and it does: it constrains 'task' to plain words with a 500-character ceiling and specifies 'country' as an optional 2-letter code. Neither the length bound nor the country format appears in the schema, so this is genuine added meaning rather than restatement. It does not explain how country affects matching beyond narrowing results.

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 concrete verb and resource: describe a need in plain words and receive the matching tool or API. The deterministic keyword-match framing makes clear it is a discovery/lookup tool, distinguishable from the verification and snapshot-search siblings. It stops short of naming a sibling explicitly, so it is clear but not maximally 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?

Gives the operative context: supply a task description in plain words and optionally a 2-letter country to narrow the match. This tells an agent when the tool applies (tool discovery from natural language) without stating exclusions or naming an alternative path, so it is clear guidance rather than a full when/when-not rubric.

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

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

With no annotations, the description carries the full burden and does reasonably well: it discloses the returned payload (phone number, diagnostic fee, specialist hours, current on/off-duty status), states the number is answered 24/7 by a named AI dispatcher, and explicitly clarifies no booking occurs, implying a side-effect-free read. Remaining gaps are permission/auth needs and behavior on the negative branch.

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 leading question front-loads the decision the agent needs, followed by a compact payload list and a closing constraint. Every clause carries information, though "specialist hours and on/off duty now" is slightly compressed to the point of ambiguity.

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 and no annotations, so the description appropriately substitutes by listing the return fields. Combined with one required parameter, the definition is adequate, with only the negative-case behavior and ZIP format left unclear.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It does add the meaningful constraint that the ZIP must be a California ZIP, which is not in the schema, but it gives no format guidance (5-digit vs ZIP+4) or behavior for invalid/out-of-area input, leaving the single required parameter only partly specified.

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 (appliance repair dispatch coverage) and a specific scope (a California ZIP), and it enumerates what the answer contains. An agent immediately knows this is a coverage-check lookup, not a booking or search tool, and the sibling tools are unrelated so no differentiation is required.

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 "No booking: the person calls the number" explicitly rules out the most likely wrong expectation (that this tool schedules a repair) and tells the agent the follow-up path is a phone call. It also implies applicability only to California ZIPs, though it does not state what to do for out-of-state or invalid ZIPs.

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?

No annotations exist, so the description carries the full burden, and it discharges most of it: it discloses the snapshot (non-live) nature, that live_active_verified is always false, that the agent must confirm at verify_url in every answer, that results are not an FCRA consumer report, and how unloaded states respond. It does not state rate limits, data freshness/as-of date, or coverage completeness per state, so it falls one notch short of the top.

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 and front-loaded, putting the snapshot qualifier and state list first and the critical live_active_verified/FCRA caveats after the filter mechanics. The state enumeration appears twice ('States accepted' vs 'loaded now'), which is meaningful but reads as slight redundancy, and the telegraphic fragments cost a little readability.

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 7-parameter read tool with no output schema, the description covers the essentials an agent needs to call it correctly: filters, limits, per-state availability, and the required downstream step of confirming at verify_url. It does not sketch what a result record contains beyond verify_url/live_active_verified, nor the as-of date of the snapshot, which leaves non-critical gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate and largely does: business_name requires 3+ characters, county is valid for CA/TX/FL but not WA, city narrows, limit range is 1-10 over the schema default of 5, and state's accepted vs currently loaded values are spelled out. license_number and zip formats/match behavior are left undefined.

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 ('Search a SNAPSHOT of public contractor-licence data') and enumerates the four state sources with their registries (CSLB, TDLR, DBPR, L&I), which lets an agent distinguish it from the CA-only sibling search_cslb_bulk_snapshot without opening a schema. It stops short of explicitly naming that sibling or any other alternative.

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 concrete usage context: supply license_number, business_name (3+ chars), zip and/or county with the CA/TX/FL-only caveat, city narrows, limit 1-10, and a clear when-not via 'A state not loaded yet answers state_unavailable'. No routing guidance relative to the sibling tools such as search_cslb_bulk_snapshot or extract_web_context.

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

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

With no annotations, the description carries the burden and does real work: it discloses the snapshot data vintage, that live_active_verified is always false, and a result cap of up to 10. It omits permissions, rate limits, and pagination behavior, which are the remaining gaps for a data-retrieval tool.

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 dense sentences, front-loaded with the resource and the critical 'snapshot, not live' caveat. The '1.0.0 name for...' preamble is slightly awkward metadata that costs a little readability but also carries migration 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 a 5-parameter, no-output-schema lookup tool, the description covers data source, searchable fields, result cap, and the key live_active_verified caveat. Only the limit parameter semantics and any return-field shape beyond live_active_verified are 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 0%, so the description must compensate, and it does: it enumerates license_number, business_name (with a 3+ character minimum the schema does not state) and zip, plus the optional city filter. The limit parameter and its default of 5 are never mentioned, though the 'up to 10 results' cap partially explains it.

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: search a SNAPSHOT of California CSLB's public bulk contractor-license list, and explicitly frames it as the state-CA variant of search_contractor_license_snapshot. The snapshot-vs-live distinction and the searchable fields let an agent identify it 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?

Clearly signals context: use this for snapshot bulk-list data, and 'this is not a live CSLB lookup' warns against expecting current status. It implies the sibling snapshot tool covers other states, but never states when to prefer it over search_contractor_license_snapshot explicitly, so routing is partly inferred.

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

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

With no annotations, the description carries the full burden and does well: it discloses what is inspected, the returned fields (risk_score and accept/reject), and a concrete quota ('20 checks per day'). It omits auth requirements and latency, and doesn't explicitly state it performs no mutation, but the depth of disclosed behavior is well above baseline.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence with the risk domain and checks front-loaded, followed by return values and the quota. Every clause earns its place with 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, but the description names the two return values and enumerates the checks performed, so an agent understands both inputs and outputs. Minor gaps: no note on error behavior for malformed input or what risk_score's scale means.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. It clarifies that exactly one address is accepted and, via the 'gmial.com -> gmail.com' example, gives a concrete sense of the input format. With only a single required string parameter this is close to sufficient, though it never states expected normalization or validation of the input.

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/check) and resource (one email address) and immediately narrows the purpose to 'signup-abuse risk', enumerating the exact checks (disposable domain, MX, role mailbox, free provider, typo suggestion). An agent knows precisely what this does and it is unmistakable given the unrelated siblings.

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 'signup-abuse risk' framing implies the use case (validating emails at signup), but there is no explicit when-to-use/when-not guidance or named alternative. With unrelated siblings this is unlikely to cause misrouting, so implied usage is adequate but not strong.

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

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

With no annotations supplied, the description carries the full burden and does well: it discloses that data is offline (not a live carrier lookup), names a concrete accuracy limitation (US/Canada VoIP undetected), and states a rate limit (free 30 checks/day). It does not mention authentication or what happens when the quota is exhausted, which are the remaining behavioral gaps.

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 the capability and coverage front-loaded, followed by the accuracy caveat and the quota. Every clause carries information; nothing is repeated from the name or 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?

For a 2-parameter tool with no output schema and no annotations, the description supplies the return-value inventory, the data-source caveat, and the rate limit, which is nearly everything an agent needs. The one real omission is semantics for 'default_country', which leaves the caller guessing how national-format input is resolved.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for 2 parameters, so the description must compensate and only partly does. It references country and national format, hinting that a country context is needed for parsing, but never explains the 'default_country' parameter (its US default or when to override it) and gives no format guidance for the 'phone' argument itself.

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 ('Check one phone number') and immediately scopes it with coverage (245 countries/territories, offline data). It also enumerates the returned fields (E.164/national format, country, region, time zones, line type, risk_score, accept/review/reject), so an agent can tell it apart from the sibling verify_email 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?

The 'one phone number' framing implies single-record validation rather than batch, and the 'No live carrier lookup; US/Canada VoIP is not detected' sentence tells the agent when this tool's answer is not authoritative. It lacks an explicit statement of when to prefer a sibling or a live-lookup alternative, so it stops short of full routing guidance.

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