Sonatina Piano Camps

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

Goes well beyond the readOnlyHint annotation: it discloses that answers are not stored or logged, that the link does nothing transactional on its own, and it names the three diagnostic response fields (skipped, missingRequired, warnings) and what each means. This is exactly the extra behavioral context the annotations 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?

Front-loads what the tool produces, then the negative scope, then the return-field semantics. Three dense sentences with little waste, though the final sentence packing three field names is slightly listy.

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 covers the return-value semantics (skipped, missingRequired, warnings), the side-effect profile, and the key vocabulary source. Nothing an agent needs to invoke it 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 75% and the description adds real meaning on top: answers must use keys from get_enrollment_form, productId is a week and may be omitted to let the person choose, and paymentOption corresponds to a week's paymentOptions label. Enum and nested-object shape are left to the schema, which 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 and resource ('builds a link to the program's Jotform with the person's answers filled in') and immediately clarifies the scope boundary against what an agent might assume (does not enroll, reserve, or charge). Easily distinguished from get_enrollment_form and get_catalog.

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?

Explicitly routes the agent to get_enrollment_form for the valid answer keys and explains that the recipient must still open, review, accept waivers, pay, and submit themselves. It gives clear context for when this tool is the right call, though it does not contrast against get_catalog or state prerequisites for the program/product pairing beyond the schema.

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 and openWorldHint=false, yet the description still adds genuinely useful behavior: session dates carry no year and must be resolved via `year` or `nextYear.year`, some current sessions may already be over, `nextYear` is only populated once dates are posted, and no seat counts are returned. These data quirks are exactly the kind of detail annotations cannot convey, though return shape/pagination is left implicit.

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 content payload is front-loaded in the first clause, followed by the disambiguation rule and the sibling pointer. Every sentence carries distinct information — contents, year caveat, staleness warning, sibling routing, and the read-only/no-seat-count constraints — with no restatement of the name or 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?

There is no output schema, so the description must carry the return contract, and it does: it names the major sections (programs, dates, tuition, `nextYear`, online offerings, policy FAQ) and flags what is absent (seat counts). Combined with a zero-parameter schema, nothing an agent needs to call it 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?

With zero input parameters there is nothing for the description to disambiguate, so the baseline applies. The `year` and `nextYear.year` references describe output fields rather than inputs, which is helpful framing but not parameter documentation.

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 enumerates precisely what the catalog contains — this year's programs with session dates and tuition, next year's under `nextYear`, online offerings, and the policy FAQ — so the resource and its scope are unambiguous. It is clearly distinguishable from `get_enrollment_form`, which it explicitly characterizes as covering only weeks still ahead.

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 establishes context for use (program/date/tuition/policy lookup) and points the agent at `get_enrollment_form` when the need is future weeks rather than the full catalog. It stops short of an explicit when-not-to-use rule against `build_enrollment_link`, but the routing guidance it does give is concrete.

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 and openWorldHint=false; the description restates "Read-only" and, more usefully, discloses the shape of the returned data (weeks, dates, pay-in-full/deposit prices, enrollment-open flag, prefillable questions with kind/choices/required, who fills it, outstanding tasks) despite there being no output schema. It does not cover failure modes (e.g. unknown or inactive program) or caching/freshness.

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 payload is front-loaded in a single dense sentence, followed by a compact program legend that is genuinely necessary. The main sentence is long and list-heavy, but no clause is redundant with structured fields except the brief "Read-only" restatement.

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 only one parameter, no output schema, and read-only annotations, the description supplies everything an agent needs: the return payload's contents, the program legend, and the interview-preparation context. Nothing material is missing for a tool of this complexity.

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 carries the burden, and it does so completely: every enum value is glossed with its real-world meaning (sonata = adult week-long camps, intermezzo = adult long weekends, capriccio = Capriccios & Suites, sonatina = children's Summer Sonatina, virtual = online courses). This adds genuine semantic value beyond the bare enum list.

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 (get) and resource (one program's enrollment form) and enumerates exactly what the payload contains: upcoming weeks with prices and open/closed status, prefills for questions, who must fill it in, and remaining tasks. This is clearly distinguishable from get_catalog (programs/courses) and build_enrollment_link (link creation).

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 framing "Everything needed to interview someone for one program's enrollment form" implies the use case (prepping an enrollment interview), but there is no explicit when-to-use, when-not, or named alternative such as build_enrollment_link for actually creating a link. The agent must infer the boundary from the purpose alone.

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