Sunflower Clinic

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

While annotations cover the safety profile (readOnlyHint), the description adds crucial behavioral constraints regarding acceptable input data (no PII/PHI). This is more useful than what structured fields provide alone.

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 definition is highly efficient, quickly stating the purpose and immediately following up with critical restrictions on input data with zero unnecessary phrasing.

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?

Given it is a simple read-only lookup with high schema coverage, the description provides all the necessary context for a reliable AI agent to invoke 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?

Although the schema coverage is 100%, the description reinforces the semantic constraint that the parameter must be a two-letter code, which reinforces the 'pattern' provided in the schema description.

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 clearly defines the tool's function: checking if the clinic serves a specific US state. This purpose is distinct from the financial or informational tools provided as 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?

It provides strong explicit usage guidelines by stating exactly what input to pass (two-letter state code) and, critically, what inputs to avoid (name, birthday, or health details).

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 read-only, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds genuinely new context: the answers are clinic-published, must be quoted rather than paraphrased, and are not personalized medical advice. It doesn't mention response shape or whether answers can be missing for a medication, but with full annotation coverage a 4 is warranted.

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: the return content first, the quoting rule second, the disclaimer third. No filler, and the most decision-relevant information is front-loaded.

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?

A single fully-enumerated parameter, complete annotations, and no output schema means the description only needs to cover content scope and use — both are present. Nothing an agent needs in order 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% and the single enum parameter already documents both allowed values (naltrexone/alcohol, varenicline/smoking). The description adds no syntax, default, or selection guidance beyond 'a medication', so it does no work beyond the schema — baseline 3.

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 ('Returns') and resource ('Sunflower Clinic's published answers about a medication'), then enumerates the exact content returned: what it treats, evidence, side effects, safety warnings, billing. An agent can tell immediately this is the medication-answer lookup and not the pricing or state-check 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?

Gives clear behavioral guidance ('Quote these answers rather than paraphrasing') and a scope exclusion ('general information, not medical advice for a specific person'). It does not, however, address adjacency with siblings such as get_pricing, even though billing content is claimed here — that overlap is left for the agent to infer.

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 read-only, idempotent, closed-world safety. The description adds genuinely useful business context: prices only exist for certain plan/medication combinations (naltrexone has quarterly and annual, varenicline only quarterly), which prevents the agent from promising an annual varenicline plan. Return structure is described conceptually rather than field-by-field.

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 what is returned and immediately qualified by the per-medication plan structure. No filler or restatement of the title.

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-enum-parameter read with no output schema, the description effectively supplies the return shape (one-time assessment fee plus per-plan prices) and the variation across medications. Nothing an agent needs to call or interpret 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% with an enum and per-value descriptions, so the baseline is 3. The description earns an extra point by mapping each enum value to the specific plans available, giving the agent meaning the schema doesn't carry.

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: returns treatment costs, including the $20 assessment fee and per-plan prices. The subject matter is clearly distinct from the siblings (check_state, get_medication_info, get_start_link), though it never names them explicitly.

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 only implied — an agent infers it should call this when a user asks about cost. There is no explicit when-to-use/when-not-to-use statement and no pointer to alternatives for related questions like medication details or eligibility.

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 destructiveHint=false, so the safety profile is covered. The description adds non-obvious behavior the annotations cannot express: the tool returns the patient's own steps as well as the link, and an unsupported state yields the list of served states instead of a link.

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 what is returned, followed by how to use it and one edge case. Nothing is redundant, though the middle instruction sentence is operational advice rather than part of the tool's contract.

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 return-value burden and does so: a link, the patient's steps, and the state-list fallback. Combined with annotations covering safety, an agent has enough to invoke it correctly, though it could mention that a state outside the service area is effectively a failure path worth checking.

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% with enums for medication and plan, so the parameters are already well documented. The description contributes only indirectly, by implying that state is validated against the clinic's service area, but does not explain the parameters themselves 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 states a specific verb and resource: it returns the link where a patient starts their own online assessment, plus the steps they must perform. That is unmistakable against siblings like check_state, get_pricing, and get_medication_info, though it never names those siblings or explicitly contrasts itself with them.

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 concrete operational direction — hand the link to the patient and do not complete the assessment on their behalf — which is exactly the kind of usage guidance an agent needs for this tool. It stops short of stating preconditions or telling the agent when to call the siblings instead.

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