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

Annotations already declare the safety profile (not read-only, idempotent, non-destructive), so the description's job is to add context. It does: 'Preserves the original analysis revision' and 'never calls a drafting model' are non-obvious traits an agent could not infer from the schema or 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?

Two sentences, no filler, front-loaded with the action and inputs. The behavioral caveat about the drafting model is the only trailing clause and it earns its place.

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 mutation tool with a nested matrix object and no output schema, the description omits what a successful build returns and how the resulting matrix is subsequently accessed (presumably via read_compliance_matrix). The idempotencyKey schema text covers replay semantics, so the core gaps are output/next-step and matrix sub-field behavior.

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 67% (projectId and idempotencyKey documented in-schema). The description adds meaning by mapping 'optional pasted CSV/TSV' to matrixText and 'current dossier analysis' to selectedClaimVersionIds, but says nothing about the nested title or sourceFileName fields. Baseline 3 is appropriate at this coverage level.

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 and resource ('Build a review matrix') plus the two input sources (current dossier analysis, optional pasted CSV/TSV). An agent can distinguish it from the read counterpart helvabase_read_compliance_matrix, but 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?

There is no when-to-use or when-not guidance. 'From the current dossier analysis' weakly implies a prerequisite (an existing analysis), but the description never routes the agent between this, helvabase_read_compliance_matrix, or helvabase_request_matrix_changes, nor states what to do if no analysis exists.

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