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

Adds substantial context beyond the annotations: deterministic keyword-pattern matching with no LLM, advisory-only with no containment or network action, and full x402 pricing mechanics including the PaymentRequired challenge and the _meta["x402/payment"] retry path. This is exactly the operational detail structured fields cannot carry.

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-loads what it detects before provenance, safety posture, and payment mechanics. Every sentence carries distinct information; only the arXiv citation borders on filler for an invoking agent.

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?

Constraints, safety posture, and payment flow are all covered, and with no output schema the description should ideally hint at return shape (verdict/score/evidence fields), which it does not. Otherwise complete for a 3-param read 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 baseline would be 3, but the description adds real semantics: OT-zone matches are always scored HIGH, reinforcing the zone enum's meaning. The 'at least one of processes or commands' rule is echoed rather than expanded, so no full 5.

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 ('Flags') plus the exact resource: control-loop recon patterns and LOTL/RMM-tool abuse derived from caller-submitted process/command observations. The subject matter is narrow enough to be separable from siblings (dossiers, advisories, detection artifacts), though 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?

Clearly says what input is required ('caller-submitted process/command observations') and warns it is advisory-only, but never states when to reach for this versus getDetectionArtifacts or getPrecursorTtp. Usage is implied by the input type rather than prescribed.

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