finding_correct

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

Annotations only say readOnlyHint=false, idempotentHint=false, destructiveHint=false. The description adds two real behavioral facts beyond that: corrections do not overwrite existing decisions (append/history-preserving), and corrections are reviewed before being used for training. It still omits whether the write is verified, who may act as reviewer, and whether duplicates accumulate given idempotentHint=false.

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 compact sentence with the primary action front-loaded and the two key caveats attached. Nothing is padded, though the brevity comes partly at the cost of the missing detail noted elsewhere.

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?

No output schema exists, so the description should explain what a successful record produces, and with 5 undocumented required parameters it should define the inputs. It covers one behavioral nuance but leaves the agent unable to construct a call confidently without reverse-engineering the schema.

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% across 5 required parameters, so the description carries the full burden. It only gestures at the 'correction' parameter and says nothing about project, finding, reason, or reviewer, nor about the five correction enum values (NOT-A-BUG, CONFIRMED, FIXED, REGRESSION, NEEDS-MANUAL-REVIEW) or the identifier patterns.

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+resource: 'Record a human correction'. The object is clearly tied to a finding (name 'finding_correct'), and the phrase 'without overwriting decisions' scopes it as an additive annotation rather than a mutation of prior findings. It stops short of naming a sibling or explicitly describing the finding-correction workflow, so it is clear but not fully differentiated.

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?

No when-to-use guidance and no alternatives are named, despite a large sibling set (security_triage, security_report, evidence_store) that could plausibly overlap. 'review before training' hints at a downstream workflow condition but does not tell the agent when to invoke this tool versus those siblings.

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