Switchboard Finance

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

Annotations already declare readOnly, idempotent and non-destructive, so safety is covered. The description adds real behavioral context beyond that: it discloses that responses include documents usually needed, deal-breakers and an expected callback time, and it clarifies the output is general information rather than a credit decision or advice.

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?

Purpose and scope are front-loaded in the first sentence, followed by the category list, the derived-check explanation and a concrete example. It is on the dense side, but each element (categories, example, disclaimer) does useful work, so little 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?

With an output schema present, the description needn't detail return values, and all 10 parameters are schema-documented. It supplies the qualifying context (what triggers a fit, what comes back in general terms, and the advice disclaimer), making it complete enough to invoke correctly, with only the sibling-routing gap remaining.

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, but the description adds meaning by grouping amount, property value, timing and trading history and explaining what they are checked against (loan size, LVR, time to fund), implying how existing_debt and property_value combine. It stops short of fully specifying every parameter's interpretation.

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 (checks) and resource (an Australian business owner's finance need) and spells out the finance categories covered, so an agent immediately knows what this tool qualifies. It also distinguishes itself from siblings like list_products and request_callback by framing itself as a fit-check rather than a lookup or submission.

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 strongly implied through the worked example and the mention of returning a callback time, which positions this as a pre-qualification step ahead of request_callback. However, it never explicitly says when to use this versus list_products or search, nor are there stated exclusions, leaving the routing 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, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds context the annotations do not: that the payload includes the source URL for citation, which signals the intended downstream use. It stops short of noting size, truncation, or error behavior for a missing id.

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

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

Two sentences plus a compact example, with the core action ('returns the full text of one document by id') front-loaded. Nothing is padded or restated.

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

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

An output schema exists, so the description is not obligated to describe return fields, and annotations carry the safety profile; what remains is complete for a single-id lookup. The only gap is the lack of explicit routing to the 'search' sibling that supplies the id.

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 only one parameter exists, so the schema already fully documents 'id' including its format examples. The description's inline example JSON is redundant with the schema example, adding no new syntax or constraint information. 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: returns the full text of one Switchboard Finance document fetched by id. The id example ('lane:caveat') makes the lookup key unambiguous. It does not, however, name or contrast itself with the 'search' sibling that would produce that id.

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: 'by its id' plus the example id hints that this follows a search result, but there is no explicit when-to-use statement or exclusion naming 'search' as the alternative for discovery. An agent must infer the lookup-vs-discovery split.

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

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

Annotations already establish read-only, idempotent and non-destructive behavior, so the bar is lower; the description still adds genuine value by disclosing the returned metrics (loan sizes, time to fund, max LVR, rate ranges) and explicitly scoping output to category level with no lender named, plus the effect of passing lane.

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-load the purpose and the parameter behavior, with the enumeration of criteria and the example earning their space. Slightly heavy on list-like detail, 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?

With an output schema present, return values need not be documented, and the description still covers scope, the optional-parameter effect, and output granularity. The one gap is the absence of any routing cue to the sibling tools.

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, but the description goes beyond the schema by listing what a passed lane actually unlocks (security, LVR, trading history, ATO position, deal-breakers, documents, pricing, term) and showing a concrete example value.

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 ('Lists the types of business finance Switchboard Finance arranges') and narrows the audience to self-employed Australians and ABN holders, which is far more specific than the tool name alone. It does not, however, contrast itself against siblings like check_fit or search, leaving the agent to infer the boundary.

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 usage for the optional parameter ('Pass lane for one type's full criteria') and an example payload, which implies the no-arg case lists categories. But it never states when to choose this tool over check_fit, search or fetch, and no exclusions are offered.

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 non-read-only, non-destructive, idempotent and open-world, and the description goes well beyond them: it spells out the consent wording, the return values (reference number plus expected contact time), the crucial negative guarantees ('Nothing is applied for and no credit check is run'), and the exact retry semantics tied to idempotency_key. That is precisely the behavioural context an agent needs before committing a person's details.

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

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

The content is front-loaded (what it does, then consent requirement, then outcome, then caveats) and every sentence carries information. It is a dense single paragraph with some clauses that could be tightened, but there is 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 13-parameter, consent-gated, outward-facing submission with an output schema, the description covers the legally meaningful requirements, the return shape in brief, the absence of credit checks or applications, and idempotent retries. Nothing an agent needs to call this safely 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 92%, so the baseline is 3, but the description adds real meaning the schema cannot: the precise consent text that makes consent:true valid, and the duplicate-suppression behaviour of idempotency_key. It does not explain the distinction between scenario, business_purpose, or notice_shown beyond 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 states a specific verb and resource ('Sends a business owner's finance enquiry to a licensed Switchboard Finance broker') and clarifies the downstream contact channels. It also implicitly distinguishes the tool from sibling check_fit by referencing the collection notice that check_fit produces, so an agent can place it in the workflow.

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 states a hard prerequisite ('Requires consent: true') with the exact wording the person must have agreed to, and references check_fit's notice_shown, which implies ordering relative to a sibling. It stops short of an explicit when-to-use/when-not statement or naming an alternative tool for cases where the enquiry should not be submitted.

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, idempotentHint=true, and openWorldHint=false, so the safety profile is covered. The description adds value by disclosing the return content (ids, titles, source URLs) and the citation purpose, but says nothing about result limits, ranking, or empty-result behavior.

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

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

Two compact sentences plus an inline example: zero waste, front-loaded with what is searched, then what is returned. The example is embedded rather than bloating the prose.

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

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

An output schema exists, so return values need not be explained, and the one-parameter surface is fully covered. The definition is nearly complete, though it omits guidance relative to the four sibling tools an agent must choose between.

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

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

Schema coverage is 100% and the sole parameter is a simple string, so the baseline is 3. The concrete example query adds real meaning beyond the terse schema text 'What to look up' by demonstrating the natural-language granularity expected, though it doesn't specify syntax 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 (search) and resource (Switchboard Finance's published information covering finance types, criteria, and licensing), which is far more precise than the tautological tool name 'search'. It does not, however, differentiate itself from siblings like fetch or list_products, leaving that comparison to the agent.

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

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

Usage is only implied: the example query ({"query":"second mortgage LVR for a trust"}) shows the intended lookup style, suggesting this is the entry point for citation-backed research. There is no explicit when-to-use versus check_fit, fetch, or list_products, and no exclusions.

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