Yoga Dublin

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

readOnlyHint and openWorldHint already establish the safety profile, and the description goes beyond them usefully: it discloses a two-week window on teacher/studio data and, more importantly, that a broad list omits class descriptions. That omission behaviour is a non-obvious quirk an agent would otherwise trip over. Missing only volume/pagination expectations.

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, front-loaded with the returned fields before the narrowing advice, with no filler. The middle enumeration is dense but each item (discipline, studios, teachers, cheapest price) is load-bearing information about the response shape.

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, a single optional parameter, and read-only annotations, the description carries most of the burden and does so: it sketches the returned fields, the time window, and the description-omission rule. Only the absence of any note on result volume or how descriptions are truncated keeps it from full marks.

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 schema already explains that name matches part of a class name or discipline, so the baseline would be 3. The description earns an extra point by tying the parameter to an outcome the schema does not mention: supplying name is what unlocks full descriptions.

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 opens with a concrete resource definition and enumerates the payload: discipline, studios and teachers running it in the next two weeks, and the cheapest single class. That is specific and lets an agent distinguish it from a bare schedule or price lookup, though it never names a sibling tool outright despite obvious overlap with yoga_dublin_prices and yoga_dublin_studios.

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?

"Use this for what a class is like or who it suits" gives an explicit selection criterion, and the closing clause tells the agent exactly how to invoke it (narrow with name for full descriptions). It stops short of stating when to prefer yoga_dublin_prices or yoga_dublin_studios instead, so the boundary with siblings is implied rather than stated.

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 readOnlyHint=true the description discloses what the agent would otherwise have to discover empirically: that buy_url deep-links into Mindbody's cart, that passes are valid across all four studios, that contracts auto-renew so minimum_term_months must be quoted with the price, and that a variable-amount gift card is always returned alongside offers. These are non-obvious output and framing behaviors, not restatements of the annotations.

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 resource and the return shape, then usage trigger, then caveats in descending importance. Slightly dense with three separate caveats packed into the back half, but each sentence carries operational information an agent needs.

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 still tells the agent what comes back (price in euro, buy_url, an auto-renewing contract with minimum_term_months, a companion gift card). Combined with a fully documented three-parameter schema and read-only annotations, nothing material is missing 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% and both enums are documented in the schema, so the baseline applies. The description adds adjacent meaning (passes work at all four studios, gift card is a separate companion record) but contributes no filter-specific syntax or interplay guidance such as how new_students_only combines with category.

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 opening sentence names the exact resource set (class passes, intro offers, memberships) and states what each record carries (euro price plus a buy_url), which cleanly separates it from schedule/classes/teachers siblings. An agent can identify this as the pricing-and-purchase tool without opening the 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?

"Use this for anything about what something costs or how to buy it" gives a clear positive trigger, and the gift-card sentence redirects the buy-for-someone-else case. It stops short of naming a specific sibling tool or stating an explicit when-not-to-use condition.

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 declare readOnlyHint and openWorldHint=false, so the description carries the real burden and does it well: it explains that spaces_left appears only when a class is nearly full (absence means availability), that full and waitlist_open mark a closed class, and that a book_url accompanies each entry. These are non-obvious data semantics an agent could easily misread from field names 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?

Four short sentences, front-loaded with the resource and its contents, followed by availability semantics, coverage, and the time horizon. Every clause adds information; nothing restates the tool 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?

With no output schema, the description must stand in for return values, and it does so by naming book_url, spaces_left, full, and waitlist_open. It does not state the default date behaviour or result volume, though the schema covers the defaults, so the gap is minor for a read-only listing 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 coverage is 100%, so the baseline is 3; the description earns above that by adding an interpretive example for class_name (matching 'hot' returns hot yoga) and by stating the 14-day horizon, which gives meaning to the end_date bound that the schema only describes mechanically.

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 resource (class schedule) and enumerates the fields returned: what is on, where, when, who is teaching, and a book_url. It also scopes the offering types (yoga, hot yoga, Pilates, Reformer, barre, meditation) across all four studios, which lets an agent separate it from sibling tools like yoga_dublin_teachers or yoga_dublin_prices 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?

It gives concrete usage context: a 14-day forward window and an explicit filter example ('class_name=hot' for hot yoga). What it does not do is name an alternative and say when to prefer it — with a sibling literally called yoga_dublin_classes, the boundary between the two 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 declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description goes further by disclosing the shape of what comes back (address, phone, maps link, facilities per studio) and adds a genuine business fact, 'One pass works at all four', which an agent could not derive from structured fields. It says nothing about caching or how static the data is, but that is minor here.

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?

One short sentence, front-loaded with the resource and its contents, followed by a compact caveat. Nothing is repeated and every clause carries information an agent can act on.

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 burden of telling the agent what it gets, and it does so by listing address, phone, maps link and facilities. The phrase 'what each has' is slightly vague about amenity detail, but an agent has enough to decide whether to call it and what to expect.

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?

The tool takes no parameters, so there is nothing about arguments that the description could or should explain. The baseline for a zero-parameter tool applies, and the description wastes no space on argument talk.

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 the exact resource and enumerates its contents: the four studios (Rathmines, Ranelagh, Harold's Cross, Charlemont) plus address, phone, maps link and facilities. It is unambiguously distinct from the sibling tools (classes, prices, schedule, teachers, workshops). It lacks an explicit action verb, but for a zero-parameter lookup resource the purpose is still fully clear.

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 can infer this is the tool for location/contact/facility questions and that the other five siblings cover classes, pricing, schedule and staff. There is no explicit when-to-use statement and no stated exclusions or alternatives, so routing has to be inferred from the resource name.

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 readOnlyHint and closed-world scope, so the description only needs to add context, which it does: a broad list deliberately leaves bios out while a name-narrowed call includes them, and teachers may span studios. It stops short of describing pagination, ordering, or exactly which fields each teacher record carries.

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, each load-bearing: the first states the resource and its payload, the second states the filter's behavioral effect, the third redirects to the correct sibling tool. Nothing repeats the schema or 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?

With one optional parameter, no output schema and read-only annotations, the definition covers what the agent needs to call it correctly and to anticipate that bios appear only when filtering. The residual gap is minor: the shape of the returned teacher records and any result limits are unstated.

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 already documented as 'part of a teacher's name', so the baseline is met. The description still adds real meaning by tying the name filter to a behavioral consequence: only a narrowed query returns bios, so the parameter controls both matching and response richness.

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 opens with a specific verb+resource: it lists the teachers currently teaching at Yoga Dublin plus what each teaches, which is more precise than the title 'Teachers'. It also implicitly distinguishes itself from yoga_dublin_classes and yoga_dublin_studios by framing the resource as people rather than sessions or venues.

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?

Explicit routing is given in both directions: pass a name to read a bio, and use yoga_dublin_schedule to find who teaches where, because a teacher is not tied to one studio. That is a concrete when-to-use and when-to-use-a-sibling rule rather than an implied one.

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 (readOnlyHint=true, openWorldHint=false), and the description adds behavior beyond that: broad queries deliberately drop the description field, while a name-filtered query returns it. That is a non-obvious result-shaping trait an agent would otherwise discover only by trial. Minor gaps remain about how far ahead 'coming up' extends.

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, front-loaded with the resource and payload, then the filtering caveat. The field enumeration is slightly listy but each item tells the agent what it gets back, so it earns its place.

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 duty and does so by naming the fields. Two optional parameters at full schema coverage and a safe read-only annotation profile mean little else is required; only the time window implied by 'coming up' is left undefined.

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 baseline is 3, but the description adds real meaning: name is not just a filter, it is the switch that unlocks full descriptions in the response. The studio parameter's enumerated values are left entirely to the schema, which is acceptable given full 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 resource (workshops, courses, teacher trainings at Yoga Dublin) plus the fields returned (dates, sessions, studio, teacher, price, book_url), so an agent knows exactly what this returns. It is distinguishable from siblings like yoga_dublin_classes or yoga_dublin_teachers by resource type, though no sibling is named 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?

Gives one concrete usage rule: narrow with name to get full descriptions, since a broad list omits them. That is real operational guidance, but there is no explicit statement of when to prefer this over yoga_dublin_classes or yoga_dublin_schedule, leaving cross-tool routing to inference.

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