ACI Risk Indicators

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

Annotations already mark this as a safe, non-destructive read, and the description adds substantial behavior beyond them: an access-tier gate (Professional and above), an interactive sign-in side effect when the user isn't authenticated, and the important caveat that the composite is an analytical aggregate rather than an ACI Risk Indicator. It also discloses that custody/regulatory/stress fields are null for mixed-module portfolios, which materially shapes how the agent should interpret results.

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?

Five tight sentences with no filler: purpose and input bounds first, then return contents, then the analytical caveat, then access/auth. Every sentence carries information an agent needs, and nothing is repeated from the schema or annotations.

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

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

There is no output schema, so the description responsibly enumerates the return contents and warns about null module-specific fields. Combined with access requirements, the sign-in side effect, and the scope of the composite, an agent has everything needed to call and correctly interpret this 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 coverage is 100%, so the baseline is 3, but the description adds interpretation the schema lacks: that the weight is a capital weighting driving the composite, and the aggregate size window of 2–20 positions. The constraint of ~1.0 normalization is echoed from the schema, so the added value is real but modest.

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 ("Assess the composite risk of an allocation of 2–20 providers") and immediately scopes it to a portfolio rather than a single provider, which cleanly distinguishes it from siblings like get_risk_score and compare_providers. It also names the concrete outputs (composite_score, per-provider breakdown, concentration) so the agent knows exactly what this tool produces.

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 preconditions for use: an allocation of 2–20 providers with weights summing to ~1.0, Professional plan access, and a sign-in flow if unauthenticated. It does not explicitly contrast this tool with alternatives such as get_risk_score or compare_providers, so the agent must infer the routing, but the context is otherwise unambiguous.

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 a safe read operation (readOnlyHint=true, destructiveHint=false, openWorldHint=false). The description adds genuinely useful context beyond them: the Professional-plan requirement and the fact that calling it while signed out initiates a sign-in flow, which materially affects agent 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?

Three short sentences, front-loaded with the core purpose and return value, followed by access and auth constraints. Every sentence carries information; 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 one parameter, full schema coverage, and no output schema, the description compensates by summarizing what comes back (full details plus a comparison matrix) and covering access/auth prerequisites. Nothing an agent needs to invoke 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 description coverage is 100% and the single 'slugs' parameter is fully documented with minItems/maxItems. The description's '2–5 providers' merely restates the schema bounds, adding no new syntax or format meaning, 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 (compare) and resource (providers), plus the exact cardinality (2–5 side by side) and the output shape (full details plus a per-criterion comparison matrix). This implicitly and cleanly distinguishes it from the single-provider get_provider_detail 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?

The 'compare 2–5 providers side by side' framing makes the use case clear, and the plan gating (Professional and above) tells the agent when the tool is callable. It does not explicitly name an alternative such as get_provider_detail for single-provider needs, so it stops short of the top score.

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=false annotations, the description discloses two non-obvious behaviors: a plan-gated entitlement and that calling while signed out triggers a sign-in flow. That is real context the annotations cannot convey, though error and pagination behavior remain unstated.

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 action and payload contents, followed by entitlement and auth behavior in short, additive sentences. Slightly dense enumerations but no wasted clauses.

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 does so by naming the returned fields. Combined with entitlement and auth notes, it is sufficient, with only error handling left implicit.

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 100% schema coverage, so the schema already documents provider_slug as slug or UUID. The description only reinforces the 'one provider' scoping, adding no syntax or format detail 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?

States a specific verb and resource ('Get the full breakdown of one provider's current ACI Risk Indicator') and enumerates the exact contents returned: per-criterion values, weights, weighted contributions, confidence, hard caps, stress classification. This implicitly separates it from get_risk_score, but no sibling is named 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?

Usage is implied by the scope ('one provider', 'full breakdown') and the access prerequisite is stated (Professional plan and above), but it never says when to choose this over get_risk_score or compare_providers.

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

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

Annotations already declare this is a read-only, non-destructive, closed-world operation. The description adds value beyond them by disclosing two non-obvious traits: an entitlement requirement (Professional plan+) and an interactive side effect (sign-in flow is triggered when the user is unauthenticated). It stops short of describing rate limits or the shape of the returned indicator.

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 carrying distinct information (purpose, entitlement, auth behavior), with the core purpose front-loaded. Nothing is redundant and 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?

With no output schema, the description carries more of the burden, and it never says what the 'ACI Risk Indicator' actually contains (scale, buckets, or confidence). Still, the entitlement and auth-flow disclosures plus 100% schema coverage make it largely sufficient for an agent to invoke 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 coverage is 100%, so both parameters are already documented in the schema. The description's 'by slug or name' adds a mild mapping cue but does not clarify whether provider_name and provider_slug are mutually exclusive, both required, or how conflicts are resolved, 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 (Get) and resource (ACI Risk Indicator) and scopes it to 'one provider, by slug or name', which distinguishes it from the portfolio-level sibling assess_portfolio_risk. It does not explicitly name or contrast with get_provider_detail or compare_providers, so it falls short of full sibling differentiation.

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

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

Provides real usage context in the form of plan gating ('Professional plan and above') and the sign-in side effect, which tells the agent when the call is viable. However, there is no explicit when-not guidance and no pointer to alternative tools for portfolio or comparative risk questions.

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 a safe read (readOnlyHint=true, destructiveHint=false), so the description's job is to add context — and it does, disclosing the data returned ('live provider counts and criteria counts') and the auth posture ('no sign-in needed'). Pagination or result-size behavior is not addressed, but the auth disclosure is genuinely additive beyond the structured fields.

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

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

Two short sentences with no filler; the content (what is listed, what it contains) is front-loaded and the access constraint is deferred to a compact trailing clause.

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 operation with annotations covering safety and no output schema, the description covers purpose, return payload shape, and auth requirement. Nothing essential is missing, though a note on result ordering or whether counts are computed in real time would round it out.

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. Schema coverage is 100% and the empty property set is consistent with a pure enumeration call.

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 ('List ACI Risk Indicator modules') plus what the listing carries ('live provider counts and criteria counts'). It is clearly distinguishable from siblings like get_risk_score or compare_providers, though it never explicitly names what it is not.

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: as the module enumeration endpoint it is the obvious first call, but the description never says when to use it versus downstream siblings such as get_provider_detail or search_providers, nor any prerequisites beyond the access note.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: no sign-in required and tier-based result truncation (name/module/risk band only below Professional).

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 tight sentences: purpose/filters first, return fields second, access and tier caveat last. No filler; the only slight redundancy is echoing filter axes already in the schema.

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 enumerating the returned headline fields (slug, name, module, score, risk_band, subtype) plus the tier-based truncation caveat. An agent has enough to call it correctly; pagination beyond 'limit' is the only unaddressed detail.

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 all five parameters are documented in the schema including the risk_band enum values, so the baseline is 3. The description restates the same filter axes without adding format, defaults, or combination rules beyond what the schema already provides.

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) plus resource (providers with a current ACI Risk Indicator) and the available filter axes. It does not name a sibling to distinguish itself from, e.g. get_provider_detail or compare_providers, so it lands just 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?

Provides context (free-text and/or filter search) and access/no-sign-in info, but never states when to prefer this over get_provider_detail or compare_providers. Usage is implied by the verb 'search' rather than made explicit.

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