Call Desk

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

Annotations already establish read-only, idempotent, non-destructive, non-open-world behavior, and the description adds substantial extra context: exactly what each returned rule contains (disclosure requirement, timing, applicability, effective/sunset dates, in-force status, citation, verbatim quote, source URL, as-of date) plus the FCC/TCPA framing. It also disclaims 'informational, not legal advice', which is useful behavioral guidance.

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 purpose, then the invocation modes, then the enumerated return contents. It is on the longer side and the enumeration of rule fields could be trimmed, but every sentence carries information relevant to calling or interpreting the tool.

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 describing the shape and fields of each returned rule, the scope options, and the safety profile via annotations. An agent has everything needed to call it and interpret results.

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 meaning the schema does not: both parameters are optional and omitting them returns rules 'for every jurisdiction'. It also reiterates that a phone number's area code resolves to a state.

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 (list the laws requiring AI/bot/prerecorded-voice disclosure) and scopes it precisely to US states, Canadian provinces, phone numbers, or all jurisdictions. It is clearly distinguishable from siblings like list_state_calling_rules and recording_consent_rules by its AI-disclosure focus.

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 tells the agent the ways to invoke it: pass a state, a phone number, or nothing to cover 'every jurisdiction'. It gives clear contextual usage but does not explicitly name alternatives or state when a different sibling (e.g. recording_consent_rules) is preferred.

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 read-only/idempotent safety profile, and the description adds a great deal beyond that: the full set of rule sources, that it checks every possible time zone, state holiday bans and future effective dates, plus what the response contains (allowed/not, reason, window today, next allowed time, cited rules). It also discloses the 'informational, not legal advice' caveat.

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 is front-loaded in the first clause and the return contract and disclaimer close the paragraph in a sensible order. The long parenthetical catalogue of state examples is dense and could be trimmed, but each element does illustrate real jurisdictional coverage rather than padding.

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 carries the burden of describing the return payload (decision, reason, window, next allowed time, cited rules with verbatim quotes and as-of dates). For a zero-required-parameter, compliance-decision tool spanning US and Canadian law, nothing an agent needs to invoke and interpret it 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 the baseline is 3. The description's 'choose call_type' note largely paraphrases the enum descriptions already present in the schema, and the state/phone_number/at parameters are left to the schema, so little net meaning is added.

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+outcome ('Decide whether a call ... is allowed right now or at a given time') plus the precise legal corpus it applies (FCC TCPA, FTC TSR, stricter state rules, CRTC/BC). An agent can distinguish it from check_phone_number or list_state_calling_rules, which describe or list rules rather than render a yes/no decision.

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 clearly frames the decision context and explicitly tells the agent how to choose the call_type parameter (sales_automated for AI voice/prerecorded/autodialed sales), which is the main branching decision. It stops short of naming sibling alternatives or exclusions, so an agent cannot tell from this text alone when to prefer list_state_calling_rules over this 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 (which already signal a safe, read-only, idempotent, no-network operation), the description discloses failure semantics (N11 and unassigned area codes fail), the fictional_range edge case that still resolves, data provenance (NANPA, libphonenumber), and an explicit 'informational, not legal advice' disclaimer. This is substantive behavioral context not available 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?

The description is long and dense, but it is front-loaded with the core purpose and every clause carries content — return fields, risk grades, and edge cases — rather than filler. The enumeration is justified for a tool with no output schema, though it could be trimmed slightly.

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 full burden of describing return values, and it does so comprehensively: validity, E.164 form, area-code geography, service status, overlays, time zones with local time, and a graded toll-fraud risk with named reasons. Nothing an agent needs to interpret the result 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?

With one parameter at 100% schema description coverage, the schema already documents the accepted input formats (including extensions and alphanumeric forms). The description adds only the +1 geographic scope, which is context rather than parameter syntax, so the baseline of 3 is appropriate.

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

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

States a specific verb (check) and resource (a +1 phone number) and scopes it to US/Canadian/North American numbers before calling or texting. It enumerates exactly what the result covers, so an agent can distinguish it from siblings like can_i_call_now or list_state_calling_rules.

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 'before calling or texting it' clearly establishes the pre-contact validation context in which the tool should be used. It does not, however, name or explicitly exclude the sibling tools (can_i_call_now, list_state_calling_rules) that might be confused with it, leaving that routing 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 establish readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real value beyond that: it discloses the returned provenance (citation, quote, source URL, as-of date), that unverifiable rules are surfaced, and adds a scope disclaimer ('Informational, not legal advice').

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, and the second sentence covers the no-argument mode. The middle clause is a long, comma-heavy enumeration of rule types, which is informative but slightly dense; still no wasted 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?

There is no output schema, so the description carries the full burden of describing return values, and it does: rule categories, per-rule provenance fields, and the unverified-rules caveat, plus the distinct shape of the no-argument overview. An agent knows what it will get in either mode.

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 sole parameter's accepted forms (code 'OK' or name 'Oklahoma') are already documented in the schema. The description only restates the omit-for-overview behavior that the schema also notes, adding no new format or constraint detail. Baseline 3 for high schema coverage.

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 (Show/List) and resource (calling rules Call Desk holds), plus the exact scope: one US state, DC, territory or Canadian province. The enumerated rule categories (time zones/area codes, calling-hours, recording consent, AI disclosure, automated messages) make it easy to distinguish from siblings like recording_consent_rules or ai_voice_disclosure_rules, which cover only one slice.

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 defines the two usage modes: pass a state for one jurisdiction, omit it for the all-jurisdiction overview table (hours stricter than federal, no-stricter-rule states, all-party recording states). That is concrete when-to-use guidance. It stops short of explicitly naming alternatives such as can_i_call_now for a real-time decision, so it is not a 5.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, so safety is covered. The description adds meaningful context beyond that: it enumerates what is returned, discloses the no-input fallback behavior, and adds the 'Informational, not legal advice' caveat. It does not state any rate limits or authority constraints.

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 question the tool answers, then the input modes, then the return contents. The sentence listing return fields is long and dense but each element (statute, quote, source, as-of date, federal rule, bottom line) is substantive rather than 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?

With no output schema, the description carries the return-value burden and does so thoroughly, enumerating jurisdictions, statute, quote, URL, as-of date, federal rule and a cross-border bottom line. Optional-parameter behavior (empty input) is also covered, leaving no obvious gap for an agent to 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 description coverage is 100%, so both parameters are already documented, setting a baseline of 3. The description adds the either/or query mode framing ('by state or by the phone numbers on the call') and clarifies that multiple jurisdictions can be supplied at once, which is modest but real added value.

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 ('look up whether a phone call may be recorded with one party's consent or needs every party's consent') with the exact scope (US states, DC, Canadian provinces). It is clearly distinguishable from siblings like list_state_calling_rules and ai_voice_disclosure_rules, which cover different regulatory questions.

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 context for when to use it — checking recording-consent law by state or by the call's phone numbers — and explicitly covers the no-input case ('With no input, returns the lists of all-party, mixed and one-party states'). It does not name a competing sibling tool or state exclusions, so it falls just short of a 5.

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