AegisAI

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

Annotations already cover readOnly, idempotent, and non-destructive behavior. The description adds value by disclosing that the tool is free and specifically does not perform risk verification, which are meaningful behavioral traits beyond the annotations.

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 a single, front-loaded sentence with two short clauses. Every word serves a purpose, and it's appropriately concise for a tool with no parameters.

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?

Despite lacking an output schema, the description adequately explains what is returned (discovery links and payment info) and notes the tool's free nature and lack of risk verification. For a simple, parameterless tool with good annotations, this is sufficient.

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 zero parameters, the baseline is 4 per guidelines. The description adds no parameter details, which is acceptable since there are no inputs to document; schema coverage is trivially complete.

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 it returns machine-readable discovery links and x402 testnet payment information, using a specific verb and resource. It distinguishes from the sibling verify_risk by not performing risk verification.

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 mentions it is free and does not perform risk verification, which guides users away from using it for risk assessment. However, it doesn't explicitly point to verify_risk for that need, leaving the alternative implied 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?

The description discloses significant behavioral traits beyond annotations: the tool never runs for free, requires payment, and unpaid calls return a canonical payment challenge. These details are not present in the annotations (readOnlyHint, openWorldHint, etc.) and are essential for the agent to handle the tool correctly. No contradiction with annotations.

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 three concise sentences that immediately state the core purpose and then explain the payment behavior. Every sentence adds value, with no redundancy or filler. It is well-structured and 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?

The tool has complex inputs (4 parameters, nested objects) and no output schema, yet the description only covers the payment aspect and not the return format on successful verification or the meaning of the input parameters. The most unusual behavioral trait (paid verification) is disclosed, but the description leaves substantial gaps in understanding the tool's full interface, making it minimally 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?

The schema description coverage is only 25% (only 'content' has a description), and the tool description adds no parameter-level meaning. The remaining three parameters (context, sources, requestedChecks) are undocumented in both the schema and the description, leaving their semantics ambiguous despite meaningful names and enums. The description fails to compensate for the low coverage.

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 the tool's function with a specific verb and resource: 'Runs paid AegisAI risk verification.' It distinguishes this from the sibling tool get_aegis_capabilities by focusing on the verification action, and the payment mention adds a unique differentiator.

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 provides clear context for when to use the tool (risk verification) and critical operational guidance: it is paid, must be retried by an x402-aware client, and unpaid calls return a payment challenge. However, it does not explicitly contrast with the sibling tool or state when not to use it, so it stops short of a 5.

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