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

Adds real context beyond the annotations: approval is gated by validation on figures and on cross-document consistency, and requires a confirmation value. The destructiveHint=true annotation signals consequence, but the description never states what approval actually does downstream or whether it can be undone.

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 short sentences, front-loaded with the action, then the refusal gates, then the confirmation requirement. The middle clause ('the investor is otherwise the one who notices') is evocative but slightly verbose for the information it carries.

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 no explanation, and the validation gates are covered. However, for a tool flagged destructive in a fundraising pipeline, the description omits the key fact of what approval effectuates and whether the version can be un-approved.

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 documents the UUID wrappers but leaves confirmVersion and relationshipId bare; the description supplies the meaning of confirmVersion ('the version number you were shown'), which is the non-obvious one. relationshipId remains unexplained in both places.

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 ('Approve one deck version'), which is clearly narrower than siblings like fundraising_propose_deck_version or fundraising_get_deck. It never names those siblings explicitly, so the differentiation is implied rather than stated.

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?

Gives preconditions for refusal (ungrounded figure, deck/memo value mismatch) and a confirmation ritual ('name the version number you were shown'), which tells the agent how to invoke it successfully. It does not say when to reach for this versus propose_deck_version or approve_memo_version, leaving the workflow position to inference.

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