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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds the useful scoping fact that results include proposals past human review, but says nothing about ordering, volume, pagination, or what 'past review' means in practice.

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?

It is short and wastes no words, but a single sentence fragment is under-specified rather than efficient. There is no leading verb or structure to front-load what the tool returns.

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 tool with a required connection_id and an unconstrained status string, the description does far too little: it never explains valid status values, default behavior when status is omitted, or the shape of the returned proposals. There is no output schema to compensate, so these gaps fall on the description.

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 coverage is only 50%, and the undocumented parameter is precisely the important one: 'status' is a bare string with no enum and no description, so its accepted values are unknown. The description mentions review states but never maps them to the status parameter, leaving the most consequential input entirely unexplained.

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 description is a noun phrase ('Bookkeeping proposals waiting for (or past) human review') with no verb, so the listing action is only implied by the tool name. It does narrow scope to proposals pending or past review, which distinguishes it from create_proposals, but an agent must infer that it returns a list rather than, say, a count or a single item.

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 explicit when-to-use statement and no mention of alternatives; the parenthetical '(or past)' hints that the tool covers more than just pending items but never clarifies that boundary. Nothing says when an agent should call this versus list_invoices or profit_and_loss.

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