Sissoo

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: contact details are private and must not be sourced elsewhere. It doesn't state what happens with an unknown or malformed id, which would complete the picture.

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 its returned fields, followed by the privacy constraint that shapes agent behavior. No filler or redundancy.

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?

An output schema exists, so return-value documentation is not required, and the description covers the id's provenance and the privacy rule. What remains unstated is how the tool behaves on an invalid or missing practitioner id and how it relates to get_service.

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 all three parameters including lang and currency defaults are documented in the schema itself. The description only reinforces that id originates from search results and adds nothing about language or currency behavior, 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 and resource (retrieve a Sissoo practitioner's public profile by id) and enumerates what the profile contains: name, place, languages, service types with bookable sessions, and page link. It doesn't explicitly distinguish itself from the sibling get_service, but the practitioner-vs-service framing makes the resource boundary reasonably 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?

Tells the agent where the id comes from ('from search results'), which establishes the intended lookup workflow, and adds a clear negative instruction: don't hunt for phone numbers, emails or addresses elsewhere because contact happens through the Sissoo page. It stops short of naming get_service as the alternative for service-level lookups.

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 readOnly=true, idempotent=true, non-destructive, so the safety profile is covered. The description adds genuine context beyond that — it discloses that the result includes the next 6 free times each with a pre-filtered booking link, which is a non-obvious behavioral trait. However, it says nothing about error behavior or what happens for a stale/invalid id.

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?

A single compact sentence, front-loaded with the core purpose before the field list. The field enumeration is slightly redundant with the output schema but stays within one sentence and earns most of its space.

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?

An output schema exists, annotations cover the safety profile, and the description still gives a useful preview of return content. For a simple 3-parameter read tool this is sufficient, with only usage routing to siblings left unaddressed.

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 each parameter (id, lang, currency) and its default/enum-ish values already documented in the schema. The description adds no meaning beyond that, so baseline 3 applies; 'session languages' refers to session data, not the lang parameter, and could even confuse slightly.

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 ('Details of one Sissoo session by its id') and enumerates the fields returned, so the agent knows exactly what it gets. It does not explicitly differentiate itself from siblings like search_services or get_practitioner, but the 'one session by id' scoping is 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?

Usage is only implied: the id must come from search results, and the description never says when to call this versus get_practitioner or next_free_times. There are no exclusions or prerequisites stated in the description itself.

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 readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds useful context — the knowledge source is the *public* help centre and results are capped at 3 passages with links — though it doesn't say what happens on an empty/no-match result or whether answers are account-specific.

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, zero waste: purpose and covered topics first, then result shape and source. Nothing extraneous.

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 an output schema present and rich annotations, the description supplies what's missing: source system, topic coverage, and result-count expectation. Only gap is behavior on no-match or out-of-scope questions.

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 both `question` and `lang` fully documented (including allowed language values and default behavior). The description adds nothing about parameters, so the baseline 3 applies when the schema does the heavy lifting.

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 ('Answers questions about using Sissoo ... from the public Sissoo help centre') and enumerates the covered topics (booking, fees, cancelling, refunds, accounts, practitioners). This clearly separates it from the data-lookup siblings like get_practitioner and search_services.

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 topic scope makes the intended use case evident: how-to/support questions rather than entity retrieval. No explicit exclusions or named alternatives are given, but the domain listing implicitly rules out the sibling tools' territory.

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 readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral facts beyond that: results are capped at 12, times are UK local with a UTC offset, and each entry carries a pre-filled booking link — all details an agent would otherwise have to discover from the response.

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 with no filler; the core value (free times for a session), the horizon, the cap, and the timezone/link payload are all front-loaded before any secondary detail.

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 an output schema present, the description need not explain return structure, and annotations handle the safety profile; what remains is covered by the timezone note and result cap. The only soft spot is that eligibility (which service id, and whether login is needed to book) is left entirely to schema inference.

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 all three parameters (id, days, lang) are already documented in the schema, which sets the baseline at 3. The description reinforces the days range but adds nothing about the id's provenance or the lang enum beyond what the schema states.

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 and output: free start times for one Sissoo session, with an explicit horizon (1-14 days) and result cap (up to 12). This is clearly distinguishable from the sibling lookup tools (get_service, get_practitioner, search_services), which return entities rather than bookable slots.

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 intent — surface bookable slots — is implied by 'Free start times ... each with a link to the booking page', so an agent can infer this is the availability-check tool. However, there is no explicit statement of when to call it versus get_service, nor any prerequisite such as needing a service id from search results first (that hint lives only in 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?

Beyond the annotations (which already declare readOnly/idempotent/non-destructive), it discloses the result shape and cap ('up to 8 sessions with price, booking fee included, next free time, link with that date picked') and a genuinely non-obvious behavior: crisis wording returns helplines instead of sessions. It also scopes the tool's boundary by stating where booking/payment actually occur.

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 action and scope, with the exclusions placed last where an agent will still see them. The domain example list ('reiki, massage and yoga to coaching, counselling and psychotherapy') is slightly padded, but the rest of the prose is dense with useful information rather than filler.

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 9-parameter search with full schema coverage, an output schema, and complete annotations, nothing an agent needs is missing: it knows what is searched, what filters exist, what comes back, and that the tool is a safe read that cannot transact. The crisis-routing caveat removes the last realistic ambiguity.

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 extra by characterizing the required 'need' parameter as a short, free-text description and glossing the stage parameter as 'new to it, or going deeper'. The enumerated optional facets (place, format, language, timing, budget, stage) largely echo the schema, so it does not go much beyond it.

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 and resource ('Finds bookable holistic and wellbeing sessions on Sissoo'), then bounds the domain with concrete examples and states the matching mechanism ('Matches a short description of what the person is looking for'). This is clearly a discovery/search tool, distinguishable at a glance from the ID-based siblings (get_service, get_practitioner, next_free_times) and from help_article.

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 a clear usage condition (when someone describes what they're looking for) plus explicit exclusions: 'Not for emergencies or crisis support' and 'booking and payment happen on sissoo.com'. It does not name a sibling tool and the condition that would select it instead, so it falls short of the 5 bar for routing between alternatives.

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