RegPulse Compliance Oracle

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

Annotations already cover safety (readOnlyHint=true, openWorldHint=false), and the description adds genuinely new behavioral context: only rows verified against the full official page are returned, unverified cases fall back to a 'Check with your local health department' message plus an official link, and it 'never guesses'. That reliability contract is exactly what an agent needs to trust the output; only auth/rate-limit detail is absent.

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, no filler. The primary purpose and returned fields are front-loaded, with the verification/fallback caveat immediately after.

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 the return shape, and it does by listing every returned field plus the fallback response. For a read-only, two-parameter tool this is sufficient for correct invocation.

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 (state format, optional business_type examples), which sets the baseline at 3. The description only restates 'a US state and business type' without adding format, defaulting, or matching semantics beyond 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?

The description gives a specific verb and resource (get verified food license rules) and enumerates the exact fields returned (issuing agency, renewal cycle, expiry, fee, late fee, official link). It implicitly separates itself from the Florida-only sibling by scoping to 'a US state and business type', but never names the alternatives, so differentiation is left partly to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied: call this to get food license rules for a given state/business type. The description explains the data-quality behavior but never states when to prefer it over lookup_florida_license or next_renewal_date, and gives no prerequisites or 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 cover the safety profile (readOnlyHint=true, openWorldHint=false), so the bar is lower. The description nonetheless adds real behavioral context beyond them: the data source (Florida DBPR public records), a weekly refresh cadence, and an explicit staleness caveat ("may lag"), which is exactly the kind of signal an agent needs to judge result trustworthiness.

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 compact sentences with zero filler; the core action and lookup modes are front-loaded and the freshness caveat trails where it belongs.

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 stating the returned fields (status and expiry date). It omits not-found behavior and whether business-name matching is exact or fuzzy, which are the remaining gaps for a 3-param lookup tool.

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 baseline is 3. The description restates the two valid parameter pairings and the 5-digit zip format, which largely duplicates what the schema already documents rather than adding new meaning.

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 (look up) and a precisely scoped resource (Florida DBPR food service / mobile food license), with concrete entity examples (restaurants, food trucks, caterers). An agent can distinguish this from get_state_food_rules and next_renewal_date without opening a 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 invocation conditions for both modes: by license number, or by business name plus 5-digit zip. It does not name the sibling next_renewal_date or say when to prefer it over this tool's expiry field, so the alternative-selection guidance is incomplete.

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 a safe read (readOnlyHint) against a bounded dataset (openWorldHint=false); the description adds real behavioral value on top by disclosing the null-return-with-guidance behavior and the dataset's coverage boundary (verified fixed dates vs anniversary-based permits). It stops short of describing date formatting or confidence semantics on the returned values.

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, purpose front-loaded, no filler. The alternative input paths are packed into a single clause and the failure mode is stated last, which is the right ordering.

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 must carry the return contract: it states a date is returned or null with guidance, which covers the important case. It leaves the exact date format and the shape of the included 'guidance' unstated, a minor gap for an otherwise self-contained definition.

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 already 100% and states the parameters plainly, but the description adds meaning the schema lacks: that license_number and state are alternative lookup modes, that city/business_type are optional refinements on the state path, and that state only works where a verified fixed deadline exists. This conditional semantics genuinely helps an agent pick a valid argument combination.

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 ('Get the next food license renewal deadline') and spells out the two input modes: a Florida DBPR license_number for a real expiry, or a state for jurisdictions with a verified fixed yearly deadline. It does not explicitly distinguish itself from the sibling lookup_florida_license, which also handles Florida licenses, so this falls just short of 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?

Gives clear conditional usage: use license_number for Florida, state (+ optional city/business_type) for fixed-deadline jurisdictions, with a worked example ('Michigan Apr 30'). It also signals the negative case (anniversary-based permits return null). No explicit routing away from sibling tools, so 4 rather than 5.

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