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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false. The description adds meaningful behavior beyond those annotations: the exact payload composition, an evidence_id that remains stable for the finding, and organization-boundary not-found behavior. 'It changes nothing' largely repeats the annotation profile, but the org isolation and stable ID are genuine additions.

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 front-loaded with the return payload and then adds two short behavioral notes. It is compact and readable; 'It changes nothing' is redundant with the annotations, but that is only one 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 one-parameter read tool with no output schema and rich annotations, the description covers return contents, ID stability, and cross-organization behavior. The main omission is how to obtain or format finding_id, which leaves a small but real gap.

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 sole parameter has 0% schema description coverage, and the description does not explain that finding_id is a numeric string, where to obtain it, or how it relates to IDs returned by listing tools. It does note that a foreign-organization finding_id yields not found, which is a semantic addition, but that does not compensate for the missing format and acquisition detail.

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 names a specific resource ('One finding's evidence pack') and enumerates its contents: the finding, the source analysis with date window and engine version, the rule thresholds, and a stable evidence_id. It does not explicitly name a sibling alternative, but the singular 'one finding' clearly distinguishes it from the plural webops_findings listing tool.

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?

There is no explicit when-to-use statement or routing to alternatives such as webops_findings for discovery or sec_explain_finding for explanation. The only usage constraint given is that a finding from another organization returns not found, which is a boundary condition rather than guidance on when to select this tool.

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