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

Beyond the destructiveHint=true/openWorldHint=false annotations, the description discloses two behaviors an agent could not infer: a hard refusal gate tied to unscreened quotes, and that approval supersedes the prior version. It also reveals the confirmation guardrail, which is genuinely useful pre-call context. It stops short of saying whether a superseded version is recoverable.

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?

Four short sentences with no filler, and the refusal condition is front-loaded before the mechanics. The opening metaphor costs some precision but is compact rather than padding.

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 mutation's preconditions are covered. Still missing for a destructiveHint=true approval: whether the action is reversible, what the agent should do when approval is refused, and how this fits the propose-then-approve sibling flow.

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 sentence 'Confirm by naming the version number you were shown' gives real semantic meaning to confirmVersion — a stale-read guard — which the bare maxLength:20 schema does not convey. versionId is implied by 'the version', but companyId is never mentioned, leaving one of three parameters unaddressed against 67% coverage.

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 verb 'approve' is present but the object is replaced by a metaphor ('what the founder walks into the next meeting with'), so the agent must infer from the tool name that this approves a relationship memory record. No sibling is named, leaving it unclear how this differs from fundraising_approve_deck_version, fundraising_approve_memo_version, or fundraising_approve_artifact.

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?

A real precondition is stated ('refused while any quote in it carries no screening verdict'), which tells the agent when the call will fail rather than when to choose it. However, there is no guidance on its relationship to fundraising_propose_relationship_memory or fundraising_get_relationship_memory — whether approval must follow proposal is left implicit.

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