One U Education

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

Annotations already establish readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context: it discloses the model source, the verdict categories returned, and the 24-month EOI life that bounds the estimate. It doesn't state latency or data recency, but the model attribution and verdict taxonomy are strong additions beyond 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?

A single dense sentence that front-loads the verb, model, required inputs, and return payload. Every clause earns its place, though the long list of returned fields makes it slightly heavy to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a read-only, idempotent, open-world predictor with no output schema and 100% schema parameter coverage, the description is complete enough: it names the model, the inputs, and the full set of return verdicts and metrics an agent needs to interpret the response. Nothing essential 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%, so the schema already documents all five parameters, setting a baseline of 3. The description goes further by explaining what eoiMonth is for (queue position by lodgement month) and implying firstLodgedMonth's role in the 24-month expiry, adding interpretive value over the raw schema text.

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 (estimates) and resource (subclass 189 EOI invitation timing via a named queue model), and distinguishes itself from sibling get_189_invitations by describing it as a predictive estimate rather than a record fetch. An agent can route between the predictor and the raw invitation list without opening either 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?

Clear context: you give occupation and points, and optionally eoiMonth for a queue position by lodgement month. It names required inputs but doesn't explicitly say when NOT to use it versus get_189_invitations or get_eoi_backlog, so the agent must infer the predictor-vs-data distinction from the wording.

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, idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds some useful provenance context — invitations figures are 'estimated' and the cutoff projection is a 'frozen forecast' — but says nothing about freshness, refresh cadence, or failure behavior for unrecognized ANZSCO codes.

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 front-loaded sentence naming the subject first, then the returned fields. It is dense but every clause corresponds to a distinct data point, with no filler; the long comma-list is the only mild structural weakness.

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 return-shape burden and does so well, naming each field an agent will receive. Read-only annotations cover the safety side, so the only gap is operational (data freshness/staleness and error cases) rather than something needed to call the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters are fully documented in the schema (the occupation ANZSCO/URL format and the locale enum). The description only restates the 'one ANZSCO occupation' scope and adds no form error handling or locale nuance beyond the schema, 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: invitation round history for Subclass 189 (and 491 family sponsored) scoped to a single ANZSCO occupation, then enumerates the exact data returned. It is far more specific than a tautology, but it never distinguishes itself from the close sibling estimate_189_invitation, so it falls short of a 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 description implies its use by enumerating historical round data (dates, invited/not, cutoffs) and a frozen forecast, but it never states when to prefer this over estimate_189_invitation or any other sibling, nor any prerequisites. Usage is inferable from the name/content 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?

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: includeSimilar costs 'one extra upstream call', the provider result carries a processing status, and it enumerates the returned data domains.

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 identifier and purpose are front-loaded, and the includeSimilar behavior is isolated in its own sentence. The middle field enumeration is long but each item is informative 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?

With no output schema, the description carries the return-value burden and largely discharges it by enumerating the detail categories. Annotations cover the safety profile; the only real gap is what happens when a code is not found or ambiguous.

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 still adds meaning the schema lacks: includeSimilar returns 'up to 8 similar courses' (a concrete cap not in the schema) and confirms the identifier can be a code, URL or slug.

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 ('Full details of one course') and names the exact identifiers accepted (CRICOS code, oneuedu.com URL/slug). This clearly distinguishes it from the sibling search_courses, which is a list/search operation.

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 description makes the use case clear: retrieving full detail for a single known course, with includeSimilar as an opt-in expansion. It never names search_courses as the alternative for discovery, nor states any exclusions, so it falls short of a 5.

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 safety is covered. The description adds substantive behavior beyond them: the data is an end-of-month 'as at' snapshot, the default is latest, and the returned content changes shape based on occupation and points.

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 scope, then the branching rules. Three sentences with no filler, though the middle sentence packs several conditions and runs long.

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 and does so well, describing what is returned in each branch (whole stream + top occupations, single occupation with trend, above/at-point counts) so the agent knows the result shape before calling.

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 would be 3, but the description adds real interpretation: points means 'how many EOIs sit above and at that score', occupation switches the output to that occupation's pool plus trend, and month is an end-of-month snapshot. This goes beyond the raw schema text.

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+resource (EOI pool snapshot) with the exact source (Home Affairs SkillSelect) and a precise scope: backlog for subclasses 189/190/491 by points and state. An agent can separate this from get_189_invitations or get_state_nomination without opening either 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?

Clearly explains the calling contexts: omit occupation for the whole stream plus top occupations, include occupation for that occupation's pool and 12-month trend, pass points to position a score in the pool. It describes output variation by argument rather than explicit when-not/alternatives, so no exclusions are named.

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, open-world, non-destructive, so the bar is lower. The description usefully adds that includeCourses triggers 'one extra upstream call' and that skills-assessment pathways are returned by default, giving cost and default-behavior context beyond 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 core action and scope, and every listed field is relevant to a migration agent. The long enumeration in the first sentence is dense but not padded; a slightly tighter structure would help.

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 disclose the return contents, and it does so exhaustively (tasks, skill level, lists, shortage, authority, visa subclasses, invitations, nominations, DAMA). 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?

Schema coverage is 100%, so the schema already documents all four parameters including defaults and the enum. The description restates the includeCourses behavior ('up to 8 recommended courses') which largely duplicates the schema, so 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 (get full profile) and resource (one ANZSCO occupation), and enumerates exactly what the profile contains. Accepts a code or a oneuedu.com URL/slug, which clearly separates it from the search_occupations sibling.

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 implies usage by explaining accepted input formats and describing the includeCourses toggle, so an agent can tell it returns data for one known occupation. But it never names the alternative (search_occupations) or states when to reach for this versus searching first.

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 openWorldHint, so the safety profile is covered. The description adds real value beyond that by enumerating the returned content (scale, Group of Eight flag, entry requirements, campuses, intakes, average offer time, ready-made courses search url) and by flagging that a URL slug is acceptable input. No rate limits or error behavior are mentioned, but none are expected 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?

Two sentences, front-loaded with purpose and identifier format, followed by the routing hint. The field enumeration is long but each item is informational rather than filler; slightly dense but no wasted sentences.

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 compensates by listing the returned fields, and it covers both accepted input shapes plus multilingual output via the locale schema. A note on what happens for an unknown/invalid code is the only notable 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 100%, so the schema fully documents both 'school' and 'locale' including the enum and default. The description echoes the CRICOS example and the URL alternative but adds no semantics the schema lacks, 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 ('Details of an Australian education provider'), names the identifier type (CRICOS provider code) with a concrete example, and enumerates the returned fields. An agent can distinguish this from get_course, get_occupation and the search_* siblings 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?

Explicitly routes the follow-on case: 'Use search_courses with schoolCode to list its courses,' which tells the agent this tool is for provider-level detail, not course lists. It also documents the two acceptable input forms (code or school URL). It stops short of any when-not guidance or comparison against get_course/get_occupation.

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/openWorld/destructive=false, so safety is covered. The description adds genuine behavioral context: the data is 'checked against the authority's official pages,' which signals source fidelity and freshness, plus the TRA-specific pathway logic (MSA, PSA, Job Ready, OSAP, TSS). It omits any statement of coverage limits or freshness date.

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 its scope, and the second sentence is genuinely actionable. The long parenthetical authority list overlaps the authority parameter's own examples, a minor redundancy, but every other clause adds distinct information about returned 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?

With no output schema, the description carries the burden of telling the agent what comes back, and it does so comprehensively (eligibility criteria by program, English, fees, processing time, exclusions, misconceptions). Combined with annotations covering the safety profile and a fully documented schema, nothing an agent needs to call this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the schema already documents each parameter including 'TRA decides OSAP / TSS by passport.' The description reinforces the occupation+passportCountry interaction but adds no syntax, format, or edge-case detail beyond what the schema states, so the baseline of 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+resource (retrieve skills assessment rules) and names the exact domain: Australian assessing authorities' requirements. It distinguishes itself from siblings like get_occupation and get_visa_processing_times by explicitly enumerating what content it returns (qualification, experience, English, fees, processing time, exclusions).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear invocation context: 'with occupation (and passportCountry) says which apply' and 'Pass occupation alone to look up its authority and pathways,' which tells the agent how to drive the tool with different parameter combinations. It does not, however, name a sibling tool as an alternative or state when NOT to use it, so it falls short of a 5.

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, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds substantive context beyond that: it discloses the exact fields returned (status, onshore/offshore eligibility, ranking, thresholds, allocation/used/remaining places) and that figures span this and the last program year, giving the agent a sense of data shape and scope.

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, purpose front-loaded before the optional-parameter effects. Every clause carries distinct information (status, eligibility, requirements, ranking, thresholds, places, year range). It is long but not padded, so it earns its length, though the second sentence is clause-heavy.

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?

No output schema exists, so the description carries the return-value burden and does so by enumerating the fields and their time span. All seven parameters are functionally accounted for, and the tool has no required inputs, so an agent can call it correctly from this definition alone; only minor gaps remain around pagination limits and default behavior of an all-states overview.

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 100% schema description coverage the baseline is 3, but the description adds cross-parameter semantics the schema does not: occupation augments each program with acceptance and matching state invitation records, and includeOccupationList combined with state (and ideally visaSubclass/program) yields a paginated occupation list (40/page), which explains the otherwise opaque page parameter.

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 (state/territory nomination programs for subclasses 190 and 491) and enumerates the data each record contains, so an agent knows what it retrieves. The subclass scoping implicitly separates it from the 189 siblings (get_189_invitations, estimate_189_invitation), though no sibling is named explicitly and no explicit retrieval verb appears in the description body.

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 through parameter behavior: 'add occupation to see which programs accept it' and 'add includeOccupationList for a state's occupation list' describe what happens when inputs are supplied, not when to choose this tool over get_189_invitations or search_occupations. There are no explicit when-to-use statements or exclusions.

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 (readOnlyHint, idempotentHint, destructiveHint=false), so the bar is lower; the description adds genuine provenance and units beyond them, stating the data is copied from the official 'current visa pricing' table and that amounts are in AUD. It also discloses the full set of charge categories returned, though it doesn't state update cadence or staleness.

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, with the core purpose (charges for one subclass) front-loaded and the breakdown following. The long stream enumeration is informative rather than filler, though it makes the first sentence dense.

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 carries the burden of describing returns, and it does so by enumerating the charge streams and second-instalment/STAC cases plus AUD units. It stops short of stating the exact response shape or error behavior for an unknown subclass, so it is complete but not exhaustive.

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 the schema already documents both parameters (visaSubclass pattern/examples and the locale enum), so baseline is 3. The description adds only the granularity that a call covers a single subclass and its streams, which is marginal over the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb+resource (Home Affairs visa application charges) and scopes it to one visa subclass per stream, enumerating exactly what is returned (main applicant, additional applicant 18+/under 18, non-internet charge, second instalment, STAC). An agent can distinguish it from siblings like get_visa_processing_times or get_state_nomination without opening any 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?

Usage is implied by the phrase 'for one visa subclass,' which signals the required scope of the call, but no explicit when-to-use, when-not-to-use, or alternative tools are named. The agent must infer that this is the fee lookup rather than the processing-time lookup sibling.

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, so the safety profile is covered. The description adds real behavioral context: what the numbers mean (percentile finalisation times), that figures carry a Home Affairs publication date, and that the single-subclass mode attaches Home Affairs notes. It stops short of stating caching/freshness or result-size 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 sentences, no filler, and the payload description is front-loaded before the parameter guidance. The first sentence is dense (percentiles, subclass, stream, publication date) but every clause carries information an agent needs to interpret the result.

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 explains the shape of the return (four percentiles per subclass/stream plus the Home Affairs publication date) and the two invocation modes. Locale-driven language/URL behavior is left entirely to the schema, which is reasonable given 100% coverage.

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 both parameters are already documented, and the baseline is 3. The description adds only the behavioral distinction between supplying vs omitting visaSubclass ('with Home Affairs notes' vs 'list every subclass'); it adds nothing about the locale parameter 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 verb+resource ('Home Affairs global visa processing times') and goes further by naming the exact metric returned (25/50/75/90th percentile finalisation days, per subclass and stream, with publication date). This clearly separates it from siblings like get_visa_fees and estimate_189_invitation without needing their schemas.

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 tells the agent how to drive the tool: pass visaSubclass for a single visa (returned with Home Affairs notes) or omit it to enumerate every subclass. That is clear usage context, though it does not name an alternative sibling tool or state exclusions (e.g. when another tool is better).

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, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds value beyond them by disclosing that there is no upstream dependency and that one call per conversation suffices, which is genuine caching/behavioral guidance.

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 payload contents and ending with the operational note. The middle enumeration is long but each item earns its place by telling the agent exactly which filter vocabularies are available.

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 explaining returns, and it does: it lists the categories of values plus usage notes and example calls. For a zero-parameter reference tool with annotations covering safety, nothing material 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description's enumeration of returned value categories compensates for the absent output schema rather than documenting inputs.

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 scope: the vocabulary of filter values (states, cities, qualification groups, AQF levels, field-of-education codes, provider types, education types, sort values, studentLocation semantics) for search_courses. It names the sibling it serves, so an agent can distinguish it from get_course/get_school/search_courses 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?

Explicitly ties usage to search_courses and states the operational context ('No upstream call; safe to call once per conversation'), which tells the agent when this is cheap and appropriate to invoke. It stops short of stating when NOT to use it or naming an alternative reference tool, but the routing to search_courses is clear.

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, openWorldHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds real value beyond them: results are a page of compact summaries, webUrl is a user-facing oneuedu.com link, and tuition is reported for the given studentLocation. It doesn't cover result-count limits or empty-result behavior, but the added context is substantive.

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 action and scope, then the result shape and the follow-up tool. The parenthetical filter enumeration partly duplicates the schema and lengthens the sentence, but overall it is tight and 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 24 optional parameters and no output schema, the description usefully sketches what comes back (compact summaries, tuition, provider, page url, webUrl) and flags the studentLocation dependency. Remaining gaps such as pagination mechanics are handled by the schema, so the definition is nearly sufficient 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%, so every filter is already documented with enums and examples. The description merely re-lists filter categories (state/city, AQF level, field of education, fee, IELTS, length) that the schema explains in more depth, adding little beyond what structured data provides. 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+resource with scope ('Search CRICOS-registered Australian courses for international students') and names the filters and result shape. It also explicitly distinguishes itself from the sibling get_course, which handles full detail for a single course.

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 search-then-detail workflow by routing to get_course afterwards, and implies the tool is the entry point for course discovery. It does not state when a search is inappropriate (e.g. when the course code is already known), so it stops short of full when/when-not coverage.

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 the safe-read profile (readOnly, idempotent, openWorld, non-destructive), so the bar is lower. The description adds genuine value beyond them by enumerating the returned fields (occupation name, ANZSCO, lists, shortage flag, page URL), which is important because there is no output schema; it omits pagination/rate-limit or ordering 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 dense sentences, front-loaded with the core search scope before the sibling routing. Every clause carries information, though the long parenthetical enumerations of list codes and visa subclasses pad it slightly.

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 usefully enumerates the return fields, and pagination is covered by the schema, so an agent has what it needs to call correctly. It could be stronger on result ordering or whether keyword matches are partial, but nothing critical 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 description coverage is 100%, so the schema already documents every parameter, including enums and the 15-per-page default. The description only restates the occupation-list abbreviations and sample visa subclasses without adding syntax or semantics beyond the schema, 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?

Specific verb (Search) plus a precisely scoped resource (the Australian skilled occupation database, ANZSCO codes for skills assessment/migration) and named search inputs. It clearly distinguishes itself from the sibling get_occupation, so an agent can route between list-search and detail-lookup without opening either 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?

Explicitly routes the agent to the sibling get_occupation for eligibility details, assessing authority, invitation points and state nomination, which covers the primary alternative. It gives no explicit exclusion (e.g. when not to search, or relationship to list_search_options), so it stops short of the full when/when-not/alternatives bar.

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