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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false), the description discloses the non-obvious two-phase behavior: a proposal is only staged and no record is created until confirm_proposal runs. It also tells the agent not to wait for a UI click in this context. It does not detail duplicate-proposal side effects, but the highest-risk behavioral trait is exposed.

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?

The text is front-loaded with the tool's purpose and gives the workflow in the first paragraph. The MCP note partly repeats the 'pending, not recorded' point from the first paragraph, so one sentence is redundant. Overall, the structure is efficient for the amount of guidance 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?

The description covers the return value, the follow-up call, the account precondition, and the no-UI caveat, which is substantial for a tool with no output schema. It does not explicitly document categoryId/envelopeId or distinguish this from propose_transaction_edit for editing confirmed transactions. There is also minor ambiguity between 'no proposal card in this context' and the schema's email-pipeline proposal card, but the core invocation path is complete.

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 description supplies one piece of parameter semantics: validate that accountId exists and is owned by the user before calling. Beyond that, it adds no parameter-level detail; amount units, currency conversion, editsProposalId, and accountId omission rules are all left to the schema. With coverage around 60%, the undocumented categoryId and envelopeId have no compensating prose, so the dimension is adequate but not strong.

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 names the specific action and resource ('Propose a new income or expense transaction') and immediately adds the two-phase workflow, so it is not confusable with confirm_proposal. The word 'new' plus the editsProposalId guidance separates it from proposal editing, and the pending-vs-recorded distinction is unambiguous.

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?

The description explicitly frames confirm_proposal as the required next step after user approval, instructs the agent to validate account ownership before calling, and distinguishes new proposals from edits via editsProposalId. It gives clear when-not guidance for accountId in the schema (omit only in ambiguous email import; ask in chat). It does not explicitly rule out propose_transaction_edit for recorded transactions, so the guidance is clear but not exhaustive.

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