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

Annotations already declare non-read-only, idempotent, non-destructive, closed-world behavior. The description adds real substance beyond them: the request does not approve anything, does not change the source revision, and the supplied evidence text remains unverified — i.e., the side effect is a scoped request record only.

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?

Three compact sentences, front-loaded with the action and scope, then preconditions, then the effect. No filler; only the missing linkage to sibling tools keeps it from being maximally informative per token.

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 non-destructive mutation with a nested required object and no output schema, the description covers preconditions and the boundary of the side effect. It omits what happens next (review workflow, notifications) and what the call returns, which an agent coordinating with confirm_review or read_evidence_review would benefit from.

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?

With only 43% schema description coverage, the description carries extra burden, and it does explain the intent of originalRevision (echo the revision you read) and gestures at rowId and evidenceText. It says nothing about notes, sourceTitle, or the idempotencyKey replay contract beyond what the schema already documents, so compensation is partial.

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: recording a change request against exactly one matrix row at a pinned analysis revision. The word 'matrix' ties it to the compliance-matrix family and separates it from the many other request_* siblings, though no sibling is named directly.

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?

'Requires review scope and a reviewer role' and 'at the exact analysis revision you read' give prerequisite context for using it. However, there is no explicit when-to-use versus alternatives (e.g. request_review, apply/confirm approval flows) and no statement of when this is inappropriate.

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