AxenomIA AX-SCI-001 — Scientific Novelty & Evidence

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

With no annotations, the description carries the burden of behavioral disclosure. It clearly indicates a read-only operation ('Read') and lists what content is included, which is helpful. However, it does not disclose whether the passport is static or dynamic, whether it may be missing/versioned in a way that affects behavior, or what happens if the passport is unavailable.

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 resource and immediately lists its contents. Every word earns its place; no filler or repetition 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 zero-parameter read tool with no output schema, the description is nearly complete: it names the resource, the content areas, and implies a read-only operation. The only gap is that it does not explicitly state that this is the reference document to consult before using the sibling tools, which would strengthen the contextual routing.

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, so the schema provides no parameter semantics to cover. The description compensates by explaining what the returned passport contains, which is the only meaningful semantic information an agent needs. Baseline 4 for zero-parameter tools 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 states a specific verb ('Read') and resource ('versioned AX-SCI-001 Agent Passport'), and enumerates the content areas: scope, evidence rules, evaluation status, limitations, and human-review requirements. This distinguishes it from sibling tools like axenomia_human_review_gate and ax_sci_001_assess_evidence, which are action-oriented rather than informational.

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 this is a reference/read tool for understanding the passport before acting, but it does not explicitly state when to use it versus the siblings. An agent can infer it is the prerequisite lookup for the other tools, but the description does not name alternatives or exclusion conditions.

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?

No annotations are provided, so the description carries the full burden. It discloses a limitation (never approves decisions) but does not describe what the returned boundary actually looks like (format, content, or structure), nor does it mention any side effects, permissions, or preconditions. For a zero-parameter tool, more detail on the output is expected.

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 concise sentences: the first states the primary purpose, and the second clarifies a key limitation. No redundant words, and the most important information is 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 simple zero-parameter tool, the description is minimal. However, without an output schema, the agent has no idea what the returned boundary is (e.g., a string, a number, a policy statement). The description mentions 'boundary' but does not explain its nature or how to interpret it, leaving an important gap for an agent that must act on the result.

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 schema description coverage is 100%, so the baseline is 4. The description does not need to explain any parameters, and it does not introduce any implicit parameters, so the score 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 states a specific verb ('Return') and a clear resource ('the mandatory human-review boundary for AX-SCI-001'). It also explicitly distinguishes itself from siblings by stating it never approves patentability, novelty, publication, or research-priority decisions, which sets it apart from ax_sci_001_assess_evidence.

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 context about what the tool does and what it does not do (never approves decisions), but it does not explicitly name alternative tools or specify when to use this vs. siblings. The exclusion of approval tasks is implied guidance, but no direct 'use this when...' instruction is 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states the tool returns provisional evidence findings, verification depth, gaps, and next evidence needs, and that final judgments are human-gated. This gives agents an accurate expectation of output and constraints, even if it does not cover side effects or permissions, which are less relevant for a research tool.

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 with no filler. It front-loads the core function and immediately follows with output and constraint context. Each sentence earns its place, making it highly concise and well-structured.

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 tool's purpose and outlines the return value categories (provisional findings, verification depth, gaps, next needs). However, it does not explain the optional parameters or how they affect the evidence synthesis, which is a noticeable gap given the tool has five parameters and no output schema or annotations. The core behavior is clear, but parameter guidance 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 0%, so the description must compensate for undocumented parameters. It only mentions the 'research question', which maps to the required researchQuestion parameter, but provides no guidance on topic, references, maxReferences, or proposedContribution. This is minimal compensation for a schema with zero parameter descriptions.

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: it researches and synthesizes traceable scientific evidence for a research question. It also clarifies the scope of the tool by explicitly noting that final novelty, patentability, and publication judgments are human-gated, which distinguishes it from a final-decision tool. This is a clear, specific purpose statement.

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 evidence synthesis on a research question, and the human-gated note hints that this is a provisional step before human review. However, it does not explicitly state when to use this tool instead of siblings like axenomia_human_review_gate or provide when-not conditions. The context is implied rather than directly stated.

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