Artificial eXperience Intelligence (AXI)

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

Annotations already declare readOnlyHint=true and openWorldHint=false, covering the safety profile. The description adds the gate-times-BaseScore computation model and names gate categories, which is useful context, but omits return format, failure behavior, and auth or rate-limit 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?

A single front-loaded sentence that states the computation and its components without filler. 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?

The rich input schema and read-only annotations cover parameter and safety context. The description supplies the formula, but because there is no output schema, it does not describe the return value or score range; still, it is nearly complete for a calculation 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 100%, so the baseline is 3. The description adds value by tying major parameters together through the formula: safety-case, bystander-legibility, consent, and integrity gates multiplied by episode-weighted role BaseScore.

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 (compute), resource (AXI_A), and target domains, plus the formula inputs. It does not distinguish itself from the sibling axi_calculate_score, 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?

Lists applicable domains (robotaxis, driver-assistance, delivery robots, humanoids), which implies when to use it, but gives no explicit when-not-to-use guidance or alternative sibling tools. Usage is only implied.

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 safe read-only, closed-world computation, lowering the disclosure bar. The description adds a genuinely useful behavioral trait beyond the annotations: consent and integrity gates fail closed when data is missing, which tells the agent how missing inputs are handled. It stops short of describing the returned value's shape or error surface.

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 tightly written sentences with no filler, and the core purpose is front-loaded before the gating caveat. 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?

There is no output schema, so the description carries the burden of explaining the return value, and it does not — an agent cannot tell whether the result is a scalar, a 0–1 index, or an object with per-gate flags. The fail-closed note is helpful but partial. Adequate for invoking, incomplete for interpreting.

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

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

Schema description coverage is 100%, so the schema already documents every parameter, including the nested cf and integrity objects and their fail-closed behavior. The description adds only the high-level notion of multiplicative gating and does not clarify units, weighting, or interaction between ii and the integrity sub-scores. Baseline 3 is appropriate when the schema does the heavy lifting.

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: 'Compute the multiplicative gated AXI Score (AXI v2.0, Section 4.5.8) from telemetry metrics.' This clearly distinguishes the operation from a generic calculation and pins it to a spec section. It does not explicitly contrast itself with the sibling axi_calculate_autonomy_score, so it falls short of a 5 on 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?

Usage is only implied: the tool computes a score from telemetry metrics, so an agent can infer it is for scoring rather than retrieving definitions or searching papers. There is no statement of when to use this versus axi_calculate_autonomy_score or any prerequisite for the telemetry inputs. The absence of alternatives leaves the routing decision 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=true and openWorldHint=false, so the safe, local nature of the call is covered. The description adds only that three output formats exist; it says nothing about determinism or what the returned citation looks like.

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 short sentence, front-loaded with the action and resource and ending with the format options. 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 read-only, single-optional-parameter tool with no output schema, the description covers everything needed to invoke it correctly. Only the actual return shape is unstated, which is minor here.

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%, but the single parameter's enum already enumerates text/apa/bibtex. The description restates those values in prose without adding format-specific details (e.g., style variants), so it neither compensates for nor worsens the coverage gap.

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 a citation) and resource (the AXI paper), plus the supported output formats. An agent can distinguish it from siblings like axi_search_paper or axi_get_definition, though it does not explicitly name an alternative.

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 the purpose — cite the AXI paper when a citation is needed — with no explicit when/when-not guidance or mention of alternatives. For a trivial single-purpose utility this is acceptable but unhelpful.

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 declare readOnlyHint=true and openWorldHint=false, so the safety profile is already covered. The description adds genuine behavioral context by enumerating what the call yields (profile, Bridge components, guardrails, black-box tests), which the annotations cannot convey. It stops short of describing determinism or whether results are static vs. computed.

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 that names the input first and the returned artifacts second, with no filler. The inline example list is useful but makes the sentence slightly dense; a short output-orientation clause would improve scannability.

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

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

With no output schema, the description carries the burden of explaining return values and does so by listing the four output categories. Input expectations and the optional profile override are clear. Minor gap: it never explains what an 'AXI conformance profile' or 'Bridge component' is, which matters for a domain-specific 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 100%, so both parameters (system_description, profile) are already documented, including the 'force a profile instead of inferring one' override and the enum values. The description only loosely echoes the input ('a description of an AI system') without adding format or content guidance 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: it returns the applicable AXI conformance profile, Bridge components, guardrails, and conformance tests for a described AI system. The parenthetical input examples (assistant, coding agent, voice bot, etc.) sharpen the scope. It does not name or contrast with siblings such as axi_calculate_score, though the design/review framing is distinct from the scoring and citation 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 phrase 'to include in its design and plan' implies this is a design-time consultation tool, but there is no explicit when-to-use/when-not-to-use statement and no routing to alternatives like axi_calculate_score or axi_get_definition. Usage is inferable rather than stated.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuine value beyond that by enumerating what the return contains (definition, author, citation, disambiguation) — meaningful since there is no output schema — though it says nothing about the not-found case.

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 redundant clauses; the noun being defined is immediately followed by the acronym expansion and the return contents. Nothing is padded.

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 parameters and no output schema, the description carries the full burden of describing the return, and it lists the four components (definition, author, citation, disambiguation) including the explicit AXI-bus disambiguation case. This is complete for a zero-arg lookup 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?

Zero parameters, so per calibration the baseline is 4. There is no argument syntax to explain, and the description correctly does not invent any.

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 (the definition of AXI), and qualifies the scope: v2.0 paper, author, citation, plus disambiguation from similarly named terms. This is enough to distinguish it from siblings like axi_search_paper or axi_cite without opening any schema.

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

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

The description implies the canonical glossary/definition lookup use case, but never states when to prefer it over axi_search_paper or axi_cite, nor any exclusions. Usage is inferable from the purpose rather than spelled out.

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 annotation readOnlyHint and openWorldHint already convey that this is a safe, closed-world read operation. The description adds that results are ranked by relevance and include headings for grounding, which is useful behavioral context beyond the annotations, though it does not describe pagination or ranking specifics.

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 tightly written sentences, front-loaded with the core search action and followed by return-value context. Every sentence 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?

For a simple two-parameter search tool with no output schema, the description covers the essential purpose and return format. It is slightly incomplete because it does not compensate for the 0% schema coverage on parameter semantics, but otherwise adequate.

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 schema provides only types and constraints (query required, limit 1-8 default 3) but no semantic explanation. The description does not explain what the query should contain or how limit affects results, leaving the agent with no guidance on parameter meaning.

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 (full-text search) and resource (the AXI v2.0 research paper), and the second sentence clarifies what it returns. It is clearly distinguishable from siblings like axi_cite or axi_get_definition, which perform different functions.

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 usage for grounding and citation, which suggests it is a discovery tool, but it does not explicitly say when to use this versus axi_get_definition or axi_cite. Sibling differentiation is weak despite the clear purpose.

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