Create a finding

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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, and idempotentHint=false, so the safety and locality profile is covered. The description reinforces the write-to-local-store nature, which is slightly useful, but adds nothing about validation failures, duplicate handling, or what a successful persist returns.

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 single front-loaded sentence is clean and waste-free, but for a 14-parameter creation tool it is under-sized rather than appropriately concise. Every word earns its place, yet there are too few words for the tool's complexity.

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?

An output schema exists, so return values need not be explained, but the description omits the required fields (title, severity, target, description), the CWE/CVSS conventions, and how this tool relates to add_finding_evidence and update_finding. Given 14 undocumented parameters and a rich sibling set, this leaves large gaps.

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 has 14 parameters with 0% description coverage, and the description contributes no parameter meaning whatsoever. For a 14-param creation tool the description is expected to compensate for the bare schema, and it fails to do so.

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 (persist) and resource (a structured security finding) plus its destination (local finding store), so an agent knows this writes a new finding record rather than reading or updating one. It does not explicitly name siblings like add_finding_evidence or update_finding, so an agent must infer the boundary from names alone.

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 when-to-use guidance, no prerequisites, and no mention of the obvious alternatives (add_finding_evidence for attaching evidence, update_finding for edits, list_findings for reads). The agent is left to infer the workflow position of this tool entirely.

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