Recovery TLV

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

Annotations already cover read-only, idempotent, non-destructive behavior, so the bar is lower, but the description still adds real value: it discloses the INSUFFICIENT_DATA failure mode on missing safety/clinical inputs and explicitly forbids causal claims, prescriptions, and autonomous clearance. That is meaningful guardrail context an agent could not derive from 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?

Two tight sentences with the capability list front-loaded and the safety guardrail second; nothing is wasted. Density of domain jargon slightly hurts readability, but the structure is efficient and appropriately short.

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 values needn't be described, but for a 17-parameter clinical tool with zero schema documentation the description is too thin. It doesn't indicate which parameters are required per intent, how missing red_flags are treated, or how the INSUFFICIENT_DATA outcome should be handled, leaving real operational gaps.

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% across 17 parameters (red_flags nested object, pain scales, symmetry indices, trajectory enums), and the description compensates for almost none of it. It alludes to scope/fit/RTS concepts but never explains which inputs matter for which intent, how the red-flag object gates behavior, or what units the symmetry percentages use.

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 the six concrete decision functions (scope, fit, nonresponse, exercise, phase-aware RTS review, escalation) that map directly onto the intent enum, so an agent can tell what the tool covers. 'Bounded patient-routing kernel' is jargon-heavy framing, and it never states plainly that this is a clinical triage/routing decision engine rather than, say, a lookup.

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 implied by the enumerated intent areas, and the INSUFFICIENT_DATA clause hints at a data prerequisite. However, it never says when to call this versus the sibling recovery.clinical_decision.safety_screen (e.g. screen first, then fit), nor states any exclusion or ordering rule, leaving the agent to infer selection from the intent enum alone.

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 description adds genuine behavior beyond them: the fail-closed rule that omitted or UNKNOWN data can never pass the safety gate. That is a consequential rule an agent could not infer from the annotations or schema. It does not describe what the gate returns, but an output schema exists to cover that.

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 tight sentences, with the core action front-loaded and the gate rule immediately after. No filler and no restatement of the tool name.

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?

The presence of an output schema removes the need to explain return values, and the fail-closed rule covers the critical invocation risk. But for a nested seven-field clinical object with a fully undocumented 'region' parameter, an agent still lacks guidance on what region denotes and how domains map to clinical concepts.

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 must carry the burden of two required parameters and a nested seven-domain object. It adds only the domain-state constraint (must be PRESENT/ABSENT/UNKNOWN/NOT_APPLICABLE), which the enums already convey, and says nothing about what 'region' means or what each clinical red-flag domain represents.

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 ('Evaluate') and resource ('explicitly reported red-flag domains'), which is clearly distinct from siblings like recovery.clinical_decision.patient_fit or the clinical_reference retrieval tools. It stops short of explicitly naming a sibling or stating the output (a safety gate verdict), so it's clear but not maximally differentiating.

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 phrase 'explicitly reported' implies the tool screens pre-collected data rather than gathering it, and the fail-closed rule hints at the safety context. However, there is no explicit statement of when to call this versus patient_fit, nor any exclusions or prerequisites for invoking it.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds one useful piece of context — results are raw citations/source identifiers, not patient-applied recommendations — but says nothing about result volume, ranking, or empty-result behavior.

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 tight sentences; the core action is front-loaded and the second sentence carries a distinct, non-redundant constraint. No 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?

An output schema exists, so the brief mention of returning citations and source identifiers is sufficient for return values. For a one-parameter read-only search tool this is nearly complete; only query-format guidance 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?

There is a single required 'query' parameter with 0% schema description coverage and only length bounds (2–200). The description implies it is a bibliography search string, which is helpful, but adds no syntax, matching, or query-construction guidance beyond that implication.

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 ('Search') and resource ('Recovery TLV's published evidence bibliography'), and adds a scope clarification that it does not apply evidence to an individual patient, which implicitly separates it from the clinical_decision siblings. It stops short of naming which sibling to use instead, so a 4 rather than 5.

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 negative framing ('without applying them to an individual patient') hints at the boundary with patient_fit and safety_screen, but there is no explicit when-to-use statement or named alternative. An agent can infer it is for literature lookup, but must open no other schema to be sure.

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, closed-world and non-destructive, so the safety profile is covered. The description adds real scope boundaries by stating it deliberately returns generic phase-level content with uncertainty and will not produce protocols, exercise dosing, or return-to-play dates — useful expectation-setting that isn't in 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?

Two short sentences, the positive capability front-loaded and the exclusions after it. No filler, no 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?

Output schema exists so return values needn't be described, and the scope limits are well covered. The remaining gap is the 'condition' input, which is left ambiguous, plus no hint of granularity (how many phases, how broad) beyond the word 'broad'.

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% for the single required parameter 'condition', and the description says nothing about what form it takes (free-text condition name, slug, or ID) or how specific it must be for the timeline to be meaningful. With one undocumented param the description was the only place to compensate, and it doesn't.

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 — returning broad educational tissue-healing phases (plus uncertainty) — which is clearly distinct from the decision/screening siblings. It never names a sibling directly, but the negation set (no protocol, no dose, no return date) effectively fences it off from the clinical_decision tools.

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 'does not' clause implies this is the educational/reference path rather than the decision path, but there is no explicit 'use this when X, use get_evidence/safety_screen when Y' routing. An agent must infer when to prefer this over a peer reference tool.

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 read-only/idempotent safety. The description adds domain-specific behavior: data is population-level only, unavailable cohorts are not extrapolated, scans are not interpreted, and pathology is not excluded. It does not cover auth or rate limits, but adds substantial context beyond 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?

Two compact sentences, front-loaded with the action and constraint, with no redundant restatement of the name or annotations.

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 two-parameter reference lookup with an output schema and explicit safety annotations, the description covers scope and interpretation limits adequately. The main omission is body_part context and sibling routing, but the schema and output schema carry the rest.

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%; the description only alludes to an 'age cohort' and never mentions the body_part parameter or its enum values. With two required parameters, the description does not compensate for the schema's lack of parameter 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?

States a specific return: population-level prevalence data, with a cohort-availability condition. This is clear enough to distinguish from generic evidence/timeline siblings, though it does not explicitly name those alternatives.

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 a clear precondition ('only when the dataset contains the requested age cohort') and explicit non-uses (no extrapolation, no individual scan interpretation, no pathology exclusion). It stops short of naming sibling tools to use for individual interpretation or evidence lookup, so routing is incomplete.

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 a meaningful scope boundary about not being a diagnostic/scoring tool, but says nothing about what happens when no published measure exists for a condition or how results are bounded.

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 short sentences, both earning their place: the first states the function, the second states the boundary. The purpose is front-loaded with no 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?

An output schema exists so return values need no explanation, and annotations cover safety. However, with a required, entirely undocumented string parameter and a clinical-adjacent tool, the description leaves the caller guessing at the most basic input semantics.

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% for the single required parameter condition_or_region, and the description never mentions it. An agent must infer that the argument is a condition or body region name and cannot tell expected format, granularity, or whether free-text synonyms are accepted.

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: 'Return educational information about published outcome measures and thresholds.' The negative clause 'Does not score or diagnose an individual patient' implicitly separates it from recovery.clinical_decision.patient_fit, though no sibling is named outright.

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 'educational information' framing plus the explicit exclusion ('does not score or diagnose an individual patient') gives a clear condition for use and a clear condition against it. It does not name the alternative tool an agent should call when actual patient scoring is needed, so routing is only implied.

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, non-destructive, and closed-world, so the safety profile is fully covered. The description adds useful behavioral context beyond that: 'canonical' signals authoritative source-of-truth data, and the explicit exclusion of clinical inference, pricing, and booking sets clear expectations that this tool performs no computation or mutation.

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 short sentences, front-loaded with the positive capability and followed by the scope exclusions. Nothing is redundant with the schema or annotations.

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 parameters, an output schema covering return values, and complete annotations, the description needs only to state purpose and boundaries, which it does. A small gap remains in not indicating when in a workflow this identity lookup is expected relative to the identity and navigation siblings.

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 zero parameters, so there are no semantics to explain; the baseline for a parameterless tool applies. The schema and 100% coverage leave nothing for the description to compensate for.

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 uses a specific verb ('Return') plus a concrete resource ('canonical Recovery TLV identity and clinician credentials'), which an agent can map to a single read operation. The negative clause ('No clinical inference, pricing calculation or booking action') implicitly fences it off from the decision, pricing, and booking siblings, though it never names a sibling outright.

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 it should call this when it needs clinic identity or credential data and should not expect it to price or book. There is no explicit 'use this instead of get_location/get_pricing/get_scope' routing, which matters given several identity-prefixed siblings.

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 this as a read-only, idempotent, non-open-world lookup, so safety behavior is covered. The description adds one worthwhile caveat about the static nature of hours, but says nothing about data freshness in general, staleness of coordinates, or locale/tenant scoping.

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, no filler, and the disambiguating caveat is placed immediately after the content list. Every clause 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 an output schema present, the description need not explain return values, and it still enumerates the key fields. It leaves open which location is returned when no parameters are accepted (presumably implicit tenant/session scoping), which is the only material gap.

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 zero parameters, so there is no parameter semantics to describe and the baseline is 4. The description does not need to compensate for any schema gap.

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 resource concretely and enumerates the returned contents (address, coordinates, hours, contact channels), which clearly separates it from clinical reference and navigation siblings. It stops short of naming the sibling tool that handles live availability, so the separation is implied rather than explicit.

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 second sentence gives a real exclusion: do not treat the hours field as live appointment availability. That is a useful routing signal, but it never names the alternative tool (recovery.navigation.get_live_availability) nor states positively when to prefer this lookup.

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, so the bar is lower; the description still adds real behavioral context by marking the values as 'canonical' source-of-truth and by declaring a negative constraint (no estimated coverage). It does not describe failure behavior when pricing is absent.

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 tight sentences: the returned fields are front-loaded and the scope boundary follows immediately. No filler, no repetition of the tool name.

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 document return structure, and with zero params and rich annotations little else is required. The only meaningful gap is the unresolved boundary against the reimbursement sibling 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly spends no space on input semantics.

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?

Specific verb ('Return') plus an enumerated set of returned facts (session fee, duration, cancellation policy, reimbursement status), which tells an agent exactly what this resource yields. It stops short of differentiating itself from the sibling recovery.navigation.get_reimbursement, which also concerns reimbursement.

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 exclusion 'Does not estimate unverified coverage' implies this tool is for authoritative, published figures rather than estimates, but it never says when to use this instead of recovery.navigation.get_reimbursement. Usage is inferable but not routed.

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 readOnly, idempotent and non-destructive, so the description earns credit for the one thing annotations can't express: the scope boundary that this returns policy facts rather than clinical judgments. It adds no detail on freshness or source of the policy, which would have completed 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 short sentences with the returned content front-loaded and the scope exclusion second. Every clause carries information; nothing is repeated from the name or annotations.

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 needn't explain return structure, and with no parameters and full annotation coverage the only remaining gap is how the clinic is resolved in context. The definition is otherwise complete for a trivial read 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?

Zero parameters means there is nothing to disambiguate, so the baseline applies. The description correctly says nothing about inputs, matching the empty 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 (return) and enumerates the exact resource contents (inclusions, exclusions, minimum age) as factual policy. It is immediately distinguishable from sibling decision tools because it explicitly frames the output as policy data, not a judgment.

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 line 'Does not decide safety or patient suitability' implicitly routes the agent to recovery.clinical_decision.safety_screen or patient_fit when a decision is needed, which is useful context. It stops short of naming those siblings explicitly, so an agent must infer the alternative rather than being handed it.

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 and non-destructive, so the safety profile is covered. The description still adds real value beyond them by asserting the links are 'human-confirmed' (booking happens outside the system) and by explicitly forbidding the agent from claiming a booking occurred — a strong anti-hallucination guardrail. It omits any note on how the language parameter affects the returned link or labels.

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 tight sentences with no filler; the positive purpose comes first and the scope restriction second. Every sentence carries information the agent cannot get from the structured fields.

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 detail is legitimately omitted, and the read-only/closed-world annotations cover the safety side. For a single-optional-parameter navigation tool this is essentially complete, with only the missing language behavior and the sibling relationship to get_live_availability as gaps.

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 should compensate — and it says nothing about the single 'language' parameter. Mitigating this, the parameter name plus its three-value enum (he/en/es) is self-explanatory, so the practical ambiguity is small. This lands near the baseline rather than being actively misleading.

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: 'Return ... booking and WhatsApp handoff links', which is concrete and tells the agent exactly what it receives. It also carves out scope with 'never claims to create, reserve, modify or cancel an appointment', separating it from any booking action. It does not explicitly distinguish itself from the closest sibling, recovery.navigation.get_live_availability, so an agent must infer whether to check availability first.

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 implied rather than stated — the agent can infer this is the terminal step after a decision, but no sentence says 'use this when the user wants to book' nor names any alternative. The negative clause ('never claims to create...') functions as partial when-not guidance by ruling out treating this as a booking action. No prerequisites or call-ordering hints are given.

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 read-only, idempotent, non-destructive, closed-world profile, so the bar is lower. The description adds genuinely new context: the record is educational and explicitly not a patient-specific diagnosis or treatment plan, which materially shapes how an agent should present the result. It does not mention behavior on a missing or unpublished slug, keeping it from a 5.

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 short sentences with no filler, and the operation and lookup key appear first. The disclaimer sentence is short and carries real informational weight.

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 a single required parameter, full annotation coverage, and an output schema handling return values, the description covers what an agent needs. The remaining gap is the absence of guidance for slug resolution and not-found behavior, which is minor at 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 must compensate; it does so partially by stressing 'exact slug', signaling exact-match rather than substring lookup. It does not describe where slugs come from or the allowed format (the pattern in the schema is undocumented).

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 ('Return') and resource ('published condition record') plus the lookup key ('exact slug'). The word 'published' and 'exact' implicitly separate it from the sibling search_conditions tool, but the sibling is never named, leaving a small gap in differentiation.

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?

'By exact slug' implies this is the direct-lookup path when the slug is already known, which is useful context. However, it never explicitly says when to use this versus recovery.navigation.search_conditions, nor what to do when the slug is unknown.

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 safety (readOnly, idempotent, non-destructive), yet the description adds substantial behavioral context beyond them: the ~15-minute upload cadence, the 07:00-23:00 Israel-time window, overnight retention with a 48-hour staleness cutoff, and the guarantee that the tool never contacts Kuze or creates a booking. That last point is critical, since openWorldHint=true could otherwise mislead an agent into assuming a side effect.

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 is dense and nearly every clause earns its place, but it is delivered as one sprawling sentence with a long subordinate opening ('After applying the clinical routing and safety gate at https://...') that delays the actual operation. Front-loading the verb and result would materially improve scannability.

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 itemize return fields, and it still flags updated_at and the free-only guarantee. Freshness, retention, safety gating, and confirmation semantics are all covered; the only real gap is the unexplained filter parameters, which is a notable but bounded omission.

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% across 8 parameters, so the description must carry the burden and mostly does not. It explains the three-date limit that corresponds to max_results (const 3) and gestures at 'filtered to the request', but says nothing about language, from_date, after_time, before_time, patient_type, or time_preference — an agent must guess at how those interact with the three-date cap.

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 concrete artifact ('free_slots_snapshot: the available appointment times (only free times, never booked slots or patient data)') and its source, which is far more specific than the tool name alone. It implicitly separates itself from the booking sibling ('never confirms a booking'), but never names get_booking_handoff, so the differentiation is inferential rather than explicit.

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 an explicit prerequisite ('After applying the clinical routing and safety gate'), explicit exclusions ('EMERGENCY, REFER and OUT_OF_SCOPE block scheduling'), and explicit prohibitions ('Never infer availability from clinic hours or invent a missing date'). It also directs the agent to the official Kuze scheduler for verification, which is a clear when-to-go-elsewhere instruction.

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, non-destructive, and closed-world behavior. The description adds meaningful behavioral context by stating that canonical reimbursement status is returned, calculations appear only with a verified cap, and unknown policy terms remain unknown rather than being inferred.

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 description is two tight sentences with no wasted phrasing. The core purpose and the caveat about unverified caps are front-loaded effectively.

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?

Output schema existence means return values need not be fully described, and the caveat about unknown policy terms is useful. However, for a two-parameter tool with 0% schema coverage, the description omits parameter meaning and sibling-routing guidance, leaving meaningful gaps.

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 0% schema description coverage, the description should compensate by explaining insurer and sessions. It only loosely implies a health-fund context and says nothing about the insurer enum values, the required insurer parameter, or the sessions range and meaning.

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: returning health-fund reimbursement status and a calculation. It is clearer than a generic name restatement, but it does not explicitly distinguish itself from adjacent tools such as get_pricing or get_scope.

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 no explicit guidance on when to use this tool versus siblings, nor on prerequisites or exclusions. The only usage-like condition is 'only where a verified cap exists,' which constrains the result rather than telling an agent when to call the tool.

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 disclose read-only, idempotent, non-destructive, closed-world behavior. The description adds valuable clinical semantics beyond annotations by warning that matches are not diagnostic or scope-confirming, though it does not mention pagination or limit behavior.

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 description is two tight sentences with no wasted language. The core purpose is front-loaded and the important clinical caveat follows immediately.

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 simple search tool with rich annotations and an output schema, the description covers purpose and the key clinical caveat well. The only notable gap is the undocumented limit parameter, which is minor but still relevant to 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 0%, so the description must carry the burden. It clarifies that searching is done by text and language, which maps to query and language, but it does not explain limit, default language behavior, or query formatting, leaving meaningful gaps.

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 gives a specific verb and resource: 'Search the published condition index by text and language.' That is clearly distinct from clinical-decision tools, but it does not explicitly distinguish itself from the closely related sibling get_condition, so an agent may need to infer which one to use.

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 a meaningful usage boundary: a search match is 'content discovery, not diagnosis or confirmation that a patient is in scope.' That clearly steers agents away from using it as a clinical decision tool, but it does not name the preferred alternatives such as patient_fit or safety_screen.

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