australian-ai-governance-framework

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

The description discloses behavioral and business information far beyond the annotations: for example the document is returned as markdown, the free preview is read-only, printing/saving requires the paid purchase, links expire in two hours, and the result is informational only and fallible. This gives an agent a realistic sense of what happens when the call.

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 longer than most, but every sentence adds useful operational or transactional context. It starts with the top-level action ('Returns the framework.') followed by preview scope, output format, URL behavior, pricing, and disclaimer. Anything not relevant would be easy to cut, but this is information an agent likely needs.

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 is responsible for describing both the markdown output location and view_url behavior,. It also covers payment, choice of return channel, timeouts, and the prevalence of explanation. For a one-parameter retrieval go tool, this definition gives a well-rounded view an agent can handle the response expectations.

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 only parameter, session_id, is already described 100% in the schema as returned by start_australian_ai_governance_framework. The description adds the connected expiry/ownership detail, but doesn't need to repeat parameter semantics for an agent. This is a schema-carrying situation, so the baseline of 3 is appropriate.

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 clearly identifies the tool as returning an AI governance framework, specifically the National AI Centre's AI6 framework, and enumerates the practices involved. It is less a tautology, though it doesn't explicitly state how this retrieval tool differs from the sibling start/submit tools.

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

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

The flow is implicitly clear: the session_id comes from start_australian_ai_governance_framework, and links expire after the profile Is create, so the tool is clearly something to call after starting. However, the description does not explicitly say 'use this after start...' or provide when-not-to.use guidance as alternatives.

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?

With no meaningful annotation coverage, the description carries the burden and does so well: it notes the tool returns a session ID and profiling questionnaire, positions itself as a discovery/start operation, and includes the cautions 'Informational only' and 'presents a framework, not advice'. It could still be clearer about whether any organisation data is persisted beyond the session, but it is largely transparent.

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 dense but not bloated. Every sentence contributes: what it does, what legislation it covers, when to use it, what it returns, and the advisory disclaimer. It is a little long, but the length is justified by the legal scope and use-case guidance.

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?

Without an output schema, the description correctly explains the return value (session ID and profiling questionnaire) and the factors that affect the framework. It does not explicitly mention the likely follow-up steps or sibling tools, but the return value makes the 'start' nature clear enough for safe 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?

The tool has zero parameters and 100% schema coverage, so there is nothing for the description to add about parameters. It instead explains how the no-input operation is shaped by the organisation's context once the questionnaire begins, which is appropriate.

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 action ('identifies' and 'builds'), a precise resource ('Australian AI governance framework'), and a clear subject ('a specific organisation's use of AI'). It also differentiates itself from siblings by framing this as the starting step that returns a session ID and profiling questionnaire, unlike get/submit tools.

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

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

Explicitly states when to use this tool: when an Australian business asks what AI governance it needs, what rules apply, or for a governance framework/policy structure. It does not provide explicit when-not-to-use guidance, nor does it name sibling alternatives, so it misses the top tier.

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 description goes beyond the annotations by spelling out exactly what happens on re-submission: the profile is overwritten, the contact record is keyed on email, and any previously generated framework for the session is discarded. It discloses the absence of authentication and that no charge occurs at this step, which is exactly the extra context an agent needs.

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 dense but every sentence serves a purpose: scale, workflow, side effects, rendering, return contract, and usage caveats. It is not padded, no redundant repetition of the schema, and all critical caveats 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?

Even without an output schema, the description explicitly says what is returned ('session ID and status profile_saved') and what is not returned ('does not return the framework'), leaving no ambiguity. It also covers resubmittability, overwriting, contact keying, and routing to the sibling retrieval tool, so the agent has all context needed to call and post-process 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?

With schema description coverage at 67%, the description adds meaning that the schema alone does not convey. It explains that answers are question options from start_australian_ai_governance_framework, highlights the $3 million turnover threshold, and clarifies that contact.organisation becomes the document's 'Prepared for' heading so it should be the full display name.

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 pair ('Submits the organisation profile and contact details') and unmistakably ties it to the Australian AI governance framework. It further disambiguates the deliverable by saying it returns only a profile_saved status and session ID, not the framework, which distinguishes it from get_ai_governance_framework.

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 explicitly says the session ID comes from start_australian_ai_governance_framework, and that the framework is later retrieved with get_ai_governance_framework. It also gives clear behavioural context: answers should reflect actual circumstances, especially turnover, and re-submission overwrites rather than duplicates.

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