eoidata SkillSelect Data

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

Annotations already declare readOnlyHint=true and openWorldHint=false. The description adds useful context that results are aggregate EOI snapshot counts, occupations must be in the same scope, and VIP is required. It does not describe the return format or how missing or invalid occupations are handled.

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 waste. The core action and key constraints are front-loaded.

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 four-parameter tool with no output schema and 0% schema description coverage, the description is too thin. It does not explain month and state semantics, does not describe the comparison result, and gives no guidance beyond the occupations count and VIP requirement.

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 for all four parameters. It only clarifies that occupations should number two to five and share scope, and hints at VIP via 'VIP required'; it says nothing about the meaning or format of month and state.

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: 'Compare aggregate EOI snapshot counts for two to five occupations.' It is clear what the tool does, but it does not explicitly differentiate itself from sibling tools like get_eoi_snapshot, rank_occupations, or compare_pathways.

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 important constraints: two to five occupations, same scope, and VIP required. However, it does not explain when to use this tool instead of siblings such as get_eoi_snapshot or rank_occupations, nor does it state when not to use 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=true and openWorldHint=false, so safety is covered. The description adds two things annotations cannot: the data basis ('aggregate snapshot counts', i.e. pre-aggregated not live per-record data) and an entitlement gate ('VIP required'), both of which affect whether and how an agent should call it.

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 filler, with the core operation and cardinality front-loaded and the access constraint appended. Nothing repeats the tool name verbatim.

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 should say what a comparison yields (per-pathway aggregate counts, a table, etc.) — 'using aggregate snapshot counts' only hints at it. The untouched month parameter and unstated code formats leave meaningful gaps for a tool with 0% schema 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 0%, so the description carries the burden. It does convey the pathway array's shape (visa/state pairs, 2-5 items) and that a single occupation is required, but the optional 'month' parameter is never mentioned, nor are the expected formats (6-digit occupation code, MM/YYYY month, short visa/state codes).

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 (compare) and resource (visa/state pathways), plus cardinality (two to five) and scope (one occupation). This implicitly separates it from compare_occupations, though it never names that sibling explicitly.

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

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

Gives clear selection context: exactly one occupation, 2-5 pathways, and a hard prerequisite ('VIP required') that an agent must check before calling. It stops short of naming alternatives such as get_pathway_overview for single-pathway inspection or compare_occupations for cross-occupation comparison.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description adds the authentication prerequisite and a negative scope statement not present in structured fields. It does not describe the return shape (e.g., whether VIP status is a boolean or expiry date), 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 what is checked, followed by the login requirement and scope caveat. Every clause earns its place and nothing is redundant with the 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 zero-parameter read tool whose annotations cover safety, the description supplies the important remaining context: authentication requirement and what is not returned. The only gap is the absence of any indication of the response shape or behavior when not logged in, since there is no output schema.

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 the schema baseline of 4 applies and there are no parameter semantics to add or omit.

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 ('Check') and two precise resources (connected account, active VIP membership), making the scope unambiguous. The clause 'this does not expose personal profile fields' explicitly separates it from sibling profile tools like get_candidate_profile and get_grant_profile.

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 the key precondition ('Login is required') and an explicit exclusion (no personal profile fields), which implicitly routes agents to the profile siblings for that data. It stops short of naming an alternative tool directly or saying when not to call 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=true and openWorldHint=false, so the safety profile is covered. The description adds the useful behavioral note that this is a scope/guardrail lookup for downstream queries, but says nothing about rate limits, freshness, or how values are ordered or returned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One sentence, front-loaded with the verb and the enumerated resources, ending with the purpose. 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?

For a zero-parameter read-only lookup with annotations covering safety and no output schema, the description supplies enough to call it correctly. Slightly more detail on what the returned lists look like (or its relationship to get_data_catalog) would close the remaining 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 nothing for the description to disambiguate; baseline is 4. The description correctly implies no input is needed to enumerate the available dimension values.

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 clear verb (List) and enumerates the exact resources returned: EOI months, visas, states and statuses. An agent immediately knows this is a dimension-value discovery tool. It does not distinguish itself from the potentially overlapping sibling get_data_catalog, which keeps it 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?

"so another query can stay within published scope" tells the agent to call this before issuing a filtered query to obtain valid values. That is clear usage context, but no explicit exclusions or named alternatives (e.g. vs get_data_catalog) 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?

The readOnlyHint/openWorldHint annotations already establish this as a safe, closed-domain read. The description adds one genuinely useful behavioral fact — VIP access is required — but says nothing about the shape of the aggregate result, whether month is optional, or what an empty result means.

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, verb-first, with the scoping and access prerequisite front-loaded. Nothing is redundant, though the second sentence fragment ('VIP required.') is terse to the point of omitting what VIP unlocks.

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 six-parameter tool with zero schema descriptions and no output schema, the description is thin. It omits the return shape of the aggregate, the meaning of the dimension enum values, and the role of the optional month parameter, leaving key invocation details undocumented.

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

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

Schema description coverage is 0%, so the description carries full burden for six parameters. It only implicitly touches population ('submitted or invited') and dimension ('one aggregate profile dimension'); visa, state, occupation (6-digit code), and the optional month filter get no explanation at all.

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 one aggregate profile dimension' for submitted or invited EOIs. It is distinguishable from siblings like get_score_distribution or get_pathway_overview, though 'one occupation pathway' is ambiguous since the schema requires separate occupation, visa, and state parameters.

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 'VIP required' prerequisite and the submitted/invited scoping imply usage context, but there is no explicit guidance on when to choose this over get_score_distribution, get_score_position, or compare_pathways. The agent must infer the selection rule from the name.

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

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

The annotations already establish readOnlyHint=true and openWorldHint=false, so safety and world scope are covered. The description's contribution is the disclosure that only catalog-level metadata is returned, not the underlying data, which is genuinely useful context for planning a call sequence. It says nothing about the shape or size of the catalog response, but with annotations carrying the safety profile a 3 is fair.

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 with no filler. The one drawback is that the qualifier "without returning detailed data" trails at the end, where it reads as an afterthought rather than the key disambiguator it is.

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 zero-param, no-output-schema tool the description covers the essentials, but the key term "boundaries" is undefined jargon and the catalog's contents (which datasets exist, how they are named) are left entirely unspecified. An agent knows broadly what it gets back but not enough to know whether the result answers its question or whether it should call request_new_data instead.

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, which is the baseline-4 case. Nothing in the description contradicts or adds confusion about inputs, and it correctly frames this as a no-argument listing operation.

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?

Names a specific verb ("Describe") and resource ("datasets and boundaries available from eoidata.com"), and the phrase "without returning detailed data" separates it from the sibling data-fetching tools. It stops short of naming any sibling outright, so the differentiation is inferred rather than stated.

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

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

Use is only implied: an agent can guess this is a discovery/metadata tool to call before get_latest_overview, rank_occupations, or request_new_data. There is no explicit "use this when..." clause, no mention of alternatives, and no statement about whether it must be called 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 establish readOnlyHint=true and openWorldHint=false. The description adds real value beyond them: the 24-month cap, the fact results are aggregated across three status categories, and the VIP subscription requirement that gates invocation. It stops short of disclosing result granularity (monthly buckets?) or data freshness.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences with no filler; the capability and its bound come first and the access requirement last. Every clause contributes information.

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 should convey what an 'aggregate history' returns — period granularity, whether figures are counts or rates, and ordering. It covers the filters and the ceiling but leaves the response shape ambiguous, which matters for a data-retrieval tool.

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

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

Schema description coverage is 0% across four parameters, so the description carries the burden. It names three of the four filters (visa, state, occupation) and hints at the fourth via 'up to 24 months', but supplies no formats — the 6-digit occupation pattern, the state/visa code conventions, and the default month count are all unstated.

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 the resource ('aggregate submitted, invited and lodged history') and a bounded scope ('up to 24 months'). The word 'history' implicitly separates it from the sibling get_eoi_snapshot, but no sibling is named, so differentiation is left to inference.

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 notes the filters are optional and adds the access precondition 'VIP required', which is genuinely useful context. However, it never says when to reach for this versus get_eoi_snapshot, get_latest_overview, or get_invitation_rounds, so the agent must guess between closely related 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 establish read-only and closed-world behavior, and the description adds important context about access tiers and bounded scope. It does not explain pagination, rate limits, or how missing data is handled, but it meaningfully complements 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?

The description is two sentences, front-loaded with what is returned, and every clause adds useful scope or access-tier information. There is no redundant restatement of the tool name or title.

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

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

The description covers the return content and account-tier constraints, which is useful, but with four optional filter parameters, zero schema descriptions, and no output schema, it leaves significant gaps around parameter usage and result shape. It is minimally adequate but incomplete 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 0%, so the description should carry the burden for the four parameters, but it only indirectly references occupation via 'any single occupation'. It provides no semantics for visa, month, or state, and does not document formats such as the six-digit occupation code or MM/YYYY month pattern.

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', and names the outputs: bounded aggregate submitted, invited and lodged counts plus score ranges. It is clear what the tool does, but it does not explicitly distinguish itself from siblings such as get_eoi_history or get_score_distribution.

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 gives clear usage context by explaining that free accounts can query a single occupation for the latest exact pathway while VIP unlocks historical and broader scope. It does not name alternative tools or explicit exclusions, which keeps it below 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=true and openWorldHint=false, so the safety profile is covered by structured data. The description adds one genuinely non-obvious behavioral fact — a VIP entitlement gate — which is real value. It does not say whether the aggregate is precomputed/stale ("existing") or how an empty pathway is handled.

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, no filler, and the access prerequisite is stated up front at the end of the first clause set. The compression is slightly counterproductive — "closed-EOI lodged-month and score profile" packs several undefined terms into one phrase — but nothing is wasted.

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 tool with four required, entirely undocumented parameters and no output schema, the description is thin: the meaning of "pathway," the shape of the returned aggregate, and the semantics of the time window are all unstated. An agent would have to guess the parameter vocabulary before it could make a valid call.

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

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

Schema description coverage is 0%, so the description carries the full burden for four required parameters. It only clarifies that 'month' means lodgement month and that the parameters jointly identify a pathway; it says nothing about the occupation format (6-digit ANZSCO), the state code vocabulary, or valid visa values, leaving the agent to infer the patterns.

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?

It names a specific verb and resource ("Return ... aggregate closed-EOI lodged-month and score profile"), which is more than a restatement of the title. However, the load-bearing notion of "one exact pathway" is never mapped onto the four parameters, and the description does not distinguish this from near-siblings such as get_pathway_overview or get_score_distribution.

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 only guidance is the prerequisite "VIP required." There is no statement of when to call this rather than get_pathway_overview, get_eoi_history, or get_score_distribution, all of which sit adjacent in the sibling list and could plausibly serve a similar question.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds useful access context ('VIP required') and a return-size cap ('up to 12'), but does not explain what 'aggregate visa outcomes' contains or how the limit affects behavior when omitted.

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 core action and output scope. The VIP prerequisite is appended efficiently 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?

For a simple read-only retrieval tool with one parameter and no output schema, the description covers the basic purpose and access requirement. It remains vague about what an invitation round or aggregated visa outcome includes, which limits an agent's ability to know whether the result answers its question.

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 limit parameter. The description partially compensates by saying 'up to 12', which explains the maximum, but it does not mention the default value of 5, the minimum of 1, or exactly what the limit controls.

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 up to 12 published invitation rounds plus aggregate visa outcomes. It is clear enough to distinguish from sibling tools like get_occupation_invitation_cutoffs, though it does not explicitly name the difference.

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 access prerequisite ('VIP required') but no guidance on when to use this tool versus alternatives such as get_occupation_invitation_cutoffs or get_latest_overview. The agent must infer the appropriate use case.

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

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

Annotations already establish readOnlyHint=true and openWorldHint=false, so safety is covered. With no output schema, the description usefully discloses exactly which fields come back, which is the main behavioral unknown here. It does not say whether results are cached or how often the snapshot refreshes, which would have pushed it higher.

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 sentence with no filler that front-loads the return payload. Every clause names a distinct returned field, so nothing is wasted.

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 zero-parameter, read-only overview with no output schema, enumerating the returned fields is sufficient to call it correctly. The only softness is 'coverage counts', which is not defined precisely enough to predict the response shape.

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 schema has zero parameters, so there is nothing to disambiguate and the baseline applies. The description does not need to compensate for any parameter 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?

States a specific verb ('Return') and enumerates the exact items returned: snapshot month, invitation round date, processing publication, coverage counts. This distinguishes it from get_eoi_snapshot and get_invitation_rounds, which presumably return the underlying data rather than the currency metadata. It stops short of naming itself a 'freshness/currency' tool, so the intent is inferred rather than declared.

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?

There is no explicit statement of when to call this versus the many sibling data tools. Usage is only implied: an agent can reasonably infer it is a cheap pre-flight check for data currency before querying snapshots or rounds. No alternatives or exclusions are named despite a crowded sibling list.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: results are capped by account tier (1 result for free, up to 50 for VIP) and only 'published' observations are returned. It stops short of describing ordering or what a cutoff observation contains.

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 resource scope front-loaded and the tier constraint following. 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?

There is no output schema, so the description should carry more of the return-value burden, and it doesn't say what fields a cutoff observation has. Combined with the unexplained query semantics, an agent can call the tool but cannot predict what it will match or receive.

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 'query' parameter (2-120 chars, no format documented). The description says 'matching observation' but never clarifies whether the query matches an occupation name, ANZSCO code, or free text, leaving the only input underspecified in both schema and description.

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 (published occupation invitation cutoff observations), which an agent can distinguish from siblings like get_invitation_rounds or get_eoi_history. It does not explicitly contrast itself with those closest siblings, 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 explains the account-tier result limits (free = latest matching observation for one occupation, VIP = up to 50 results), which implies usage context. However, it gives no guidance on when to use this versus get_invitation_rounds, get_latest_overview, or other cutoff-related 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 establish read-only and closed-world behavior, so the description adds useful context by stating the VIP requirement and clarifying that the output involves aggregate counts and score summaries. It does not contradict the annotations, though it omits further behavioral details such as rate limits or month-default 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 compact sentences with no filler. The comparison purpose is front-loaded, followed by the VIP prerequisite.

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 read-only tool with no output schema, the description covers purpose, aggregate return content, and VIP access. It remains incomplete on parameter formats and month optionality/default behavior, which are important 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 0%, so the description must compensate, but it only generically refers to 'one occupation' and 'one month'. It does not document that occupation must be a 6-digit code, that month must follow MM/YYYY format, or that month is optional.

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: compare published visa and state pathways for one occupation in one month. It distinguishes the scope from broader siblings like compare_occupations by restricting to a single occupation, but it does not explicitly name any sibling tool.

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 when to use the tool by scoping it to one occupation and one month, and it states a prerequisite ('VIP required'). However, it does not explicitly say when to choose it over siblings such as compare_pathways or compare_occupations.

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 readOnlyHint and openWorldHint, so the description's added value is the free-vs-VIP gating ('latest summary' vs 'full breakdown') – a genuine behavioral constraint an agent needs. It stops short of detailing result shape, pagination, or what happens if free-tier requests exceed one occupation, so it's strong but not exhaustive.

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, with the core resource front-loaded. It could be tightened by folding the tier note into the same clause, but nothing is wasteful.

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 and four undocumented parameters means the description should carry more weight; it explains the tier restriction but never clarifies what month or state do or what the aggregate statistics contain. For a 4-parameter query tool this leaves an agent under-informed about 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 coverage is 0%, so all four parameters (visa, month, state, occupation) rely on the description for meaning. The description only gestures at occupation and 'pathway' and says nothing about the month (YYYY-MM) or state filters, leaving half the schema unexplained.

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 (aggregate invite-to-lodge and lodge-to-close duration statistics) with clear domain specificity. It doesn't explicitly contrast with siblings like get_eoi_history or get_latest_overview, so an agent may be unsure which duration/history tool fits best.

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 scoping ('any one occupation and exact pathway') and notes a tier difference (free = latest summary, VIP = full breakdown), which is useful context. However, it never states when to choose this over get_eoi_history, get_latest_overview, or get_score_distribution, leaving selection partly to inference.

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

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

Annotations already declare readOnlyHint and openWorldHint=false, and the description adds genuinely new context: an access prerequisite ('VIP required') and a hard result ceiling of six. It does not explain what aggregate submitted counts represent or how ties/ordering are handled.

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 with the key constraint (max six, ANZSCO grouping) front-loaded. 'VIP required' is terse to the point of being cryptic, slightly reducing clarity per word.

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, and the description covers what is returned (related occupations plus aggregate submitted counts) and the access requirement. Gaps are minor: no indication of ordering, tie-breaking, or behavior when no related occupations exist.

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?

One parameter with 0% schema description coverage, so the description must carry the burden. It hints that the input is an ANZSCO unit/minor group reference, but never states that 'occupation' is a 6-digit ANZSCO code (only the regex pattern implies that).

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 and resource ('Return ... occupations related by ANZSCO unit or minor group') with an explicit result cap of six. It distinguishes itself from siblings only implicitly via the 'related by ANZSCO group' framing, not by naming alternatives like search_occupations.

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?

No statement of when to use this versus search_occupations or rank_occupations. The only guidance is the prerequisite 'VIP required', so the agent must infer the use case from the name 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 establish readOnlyHint=true and openWorldHint=false, and the description usefully adds that VIP access is required and that scope is limited to a bounded published range. It does not define what 'bounded published scope' means in practice or clarify whether empty score buckets are included.

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 wasted language. The aggregate return is stated first, and the status/scope/VIP constraints follow 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 five-parameter read tool with no output schema and no schema descriptions, the definition covers the aggregate return and VIP prerequisite but underspecifies optional scope parameters. It is callable for the required status case, but an agent cannot confidently use the optional filters.

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 parameter meaning. It mentions 'status' and a 'bounded published scope' but leaves visa, month, state, and occupation unexplained, including their expected formats and filtering behavior.

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: returns aggregate counts by SkillSelect score, scoped to one status and a bounded published scope. It is distinguishable from siblings like get_score_position or get_eoi_snapshot, though it does not explicitly name the contrast.

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?

Provides a key prerequisite ('VIP required') and scope constraint, but gives no explicit guidance on when to use this instead of adjacent tools such as get_score_position or get_latest_overview. Usage is implied rather than fully directed.

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?

The annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds a free-account query limitation, but it does not explain return shape details such as tie handling or whether counts are exact versus estimated.

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 sentences, front-loads the core purpose, and adds the access constraint without unnecessary wording.

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 four parameters, 0% schema description coverage, and no output schema, the description is too thin. It does not clarify the roles of visa, state, and occupation, nor does it explain the returned aggregate count beyond the initial sentence.

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 parameter meaning. It clarifies 'score' and hints at occupation/pathway usage, but it does not explain the required 'visa' parameter or the optional 'state' parameter, leaving key inputs ambiguous.

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 metric: return the aggregate number of submitted EOIs at or above a score. It scopes this to one pathway, but does not explicitly differentiate the tool from siblings such as get_score_distribution or compare_pathways.

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 access context by noting that free accounts can query any single occupation in the latest exact pathway. However, it gives no explicit guidance on when to use this tool versus get_score_distribution or other score-related 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 readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuine context beyond them: 'latest published' signals data freshness/versioning (not live data) and 'VIP required' discloses an access prerequisite the agent must satisfy before calling.

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 zero waste, leading with the core action and scope, then the filters and the access precondition. 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 no output schema and no parameter descriptions, the description leaves the shape of the 'aggregate progress' response (which metrics, per-state or per-subclass breakdowns) and the meaning of 'VIP' unexplained. For a simple read-only lookup this is workable but not complete.

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 0%, so the description carries the burden; it does name both filter dimensions (state, visa subclass), which maps to the two properties. But it gives no value semantics — no mention of state abbreviations (2-5 chars) or 3-character visa subclass codes — so an agent still cannot construct valid values from the description alone.

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 a precisely scoped resource ('latest published aggregate state nomination progress'), which is clearly distinct from siblings like get_latest_overview or get_invitation_rounds. It does not explicitly contrast itself with those siblings, keeping it below 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?

'optionally filtered by state or visa subclass' implies the filtering use case, and 'VIP required' signals an access precondition. However, there is no explicit when-to-use guidance, no named alternative (e.g., get_latest_overview for non-nomination aggregates), and no statement of what happens with no filters.

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?

The annotations already declare a read-only, closed-world operation, and the description adds important behavior beyond that: only the top 20 are returned, there is no pagination or bulk export, and VIP access is required. It still does not describe response fields or error behavior, but the key result-limiting behavior is disclosed.

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 front-loaded with the core action and scope, and every sentence adds a meaningful constraint: top-20 cap, filters, no pagination/export, and VIP requirement. There is no wasted wording.

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 read-only ranking tool with no output schema, the description covers the main call constraints: result cap, filter scope, no pagination, and VIP access. It is not fully complete because it omits return fields and leaves some ambiguity about whether month is operationally required despite the schema marking no parameters required.

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 needs to compensate. It does clarify that visa and state are optional filters and that month refers to a published month, but it provides no accepted values or format guidance for visa/state and adds little beyond the schema constraints.

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/resource/metric: return the top 20 occupations by submitted EOI count, scoped to a published month and optional visa/state filters. It distinguishes this tool from broader snapshot/search tools through the top-20 ranked scope, but it does not explicitly name an alternative sibling tool.

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 useful constraints — VIP required and no pagination/bulk export — which imply this is for a capped ranking view rather than exhaustive export. However, it does not explicitly say when to use this versus siblings like get_eoi_snapshot, search_occupations, or compare_occupations.

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?

Goes beyond the annotations by disclosing access conditions: no login, no VIP membership, no submission quota required. Annotations cover the mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), but the description still omits what happens after submission (immediate ack vs. human follow-up) and that repeat calls create duplicate requests.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, each earning its place: purpose first, then access prerequisites, then content requirements. No filler or 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?

For a four-parameter, no-output-schema submission tool this covers purpose, prerequisites and what to put in the body. The remaining gap is post-submission behavior and the meaning of the two contact-related fields, which an agent would otherwise have to guess.

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 load. It explains 'what data is needed' (request) and 'how the Agent would use it' (useCase), but never mentions contact or agentName, leaving half the parameters undocumented anywhere.

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: 'Submit any unmet data need directly to the eoidata product team.' This instantly separates it from every sibling, which are all read-only retrieval tools (get_*, search_*, compare_*), since this is the only outbound submission tool in the set.

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 'any unmet data need' implicitly defines the trigger condition: use it when the catalog and existing retrieval tools cannot answer the question. It does not explicitly name a fallback path (e.g. 'check get_data_catalog first'), so it stops short of full when/when-not guidance.

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 readOnlyHint/openWorldHint annotations, the description discloses two behaviors an agent cannot see in structured fields: results are truncated to 10 and the tool cannot be used to page through the whole catalog. Match semantics (prefix vs substring, whether partial codes work) and result ordering remain undisclosed.

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 capability first and the constraint second; nothing is redundant or buried.

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 one-parameter search tool this covers the essentials, but with no output schema and no description of what a result record contains, how matches are ranked, or how to widen a too-narrow query, an agent still has gaps before calling it confidently.

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 0%, so the description carries the burden; it does add that the single query accepts either an ANZSCO code or a name, which is the key semantic. It does not state code format (e.g., 4- or 6-digit), case sensitivity, or partial-match behavior, and 'non-empty' is looser than the schema's minLength of 2.

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 ('Find ... occupations') and specifies the two accepted lookup keys (ANZSCO code or occupation name), plus a result cap. It does not explicitly differentiate itself from siblings such as rank_occupations or get_related_occupations, so it stops 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?

It gives one useful constraint — a non-empty query is required and the full catalog cannot be enumerated — which tells the agent this is a lookup, not a browse. It names no alternative tools for full-catalog listing or ranked/personalized occupation views, so the agent must infer routing from sibling names alone.

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