KitchenGrade

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description is not carrying that burden. It adds real behavior beyond structured fields: unavailable/historical/expired grades are returned as unknown rather than guessed, and it disclaims that the KitchenGrade is a third-party grade and not a food-safety guarantee.

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 compact sentences, front-loaded with the action and scope, then the data-handling caveat and disclaimer. No sentence is filler; the disclaimer is behaviorally load-bearing for a grade 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?

For a single-parameter read tool with no output schema, the description covers what it returns (grade plus dated inspection basis), how missing/expired data is handled, and the meaning of the grade. An agent has everything needed to call it correctly 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% and the single parameter is fully documented with a pattern in the schema. The description restates the format constraint and adds an example, but adds no semantics beyond what the schema already provides, so the baseline 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 (Get) and resource (KitchenGrade grade + dated inspection basis) scoped to an exact DBPR establishment ID, which cleanly separates it from the sibling search_restaurants by implying exact-key lookup rather than search. The inline ID example (2010:5816523) makes the resource unambiguous.

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 signals the precondition for use (an 'exact public DBPR establishment ID', explicitly 'not name or a private identifier'), which implies the lookup path rather than search. However, it never names search_restaurants as the alternative or states when not to call this tool, so routing 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 the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds genuine context beyond them: the data provenance (KitchenGrade-calculated, dated inspection grades, not DBPR grades) and an explicit non-guarantee caveat about food safety, which is exactly the kind of semantic caveat structured fields 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?

Three sentences, front-loaded with the core purpose and followed by output provenance and routing guidance. Dense and free of filler, though the middle clause is slightly long.

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 does step in to characterize the return (exact identifiers plus dated, independently calculated grades), which is the key missing structured information. Pagination/limit behavior is left to the schema, a minor gap for a 5-parameter search 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 80%, so the schema already documents query, city, county, and acceptable_only. The description adds little parameter-level detail beyond implying that exact establishment IDs are used downstream, 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 names a specific verb (Find) and resource (Florida restaurant establishments in KitchenGrade's captured DBPR records), and explicitly distinguishes its output from the sibling's by noting that identifiers are meant to be fed to get_restaurant_grade. An agent can tell this is a discovery/search tool versus a lookup tool 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?

It tells the agent exactly when to route elsewhere: 'Use an exact establishment ID with get_restaurant_grade before recommending a specific restaurant.' It also frames the search as a precursor step in the workflow, giving both the alternative tool and the condition that selects it.

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