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

The description clearly discloses that the tool only CREATES a pending proposal and nothing is recorded until confirm_proposal is called, which is crucial behavioral context beyond the annotations (which only mark it non-read-only and non-destructive). It also mentions the preview and instructs relaying it to the user, adding valuable behavioral detail without contradicting annotations.

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 description is longer than average but every sentence serves a purpose: main action, workflow, exclusions, parameter guidance, and the MCP note. It is front-loaded with the primary purpose and uses structured paragraphs, though the MCP note partially repeats earlier content. A slightly tighter wording would earn a 5.

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 two parameters, no output schema, and a non-trivial propose-then-confirm workflow, the description leaves nothing essential out. It covers prerequisites (lookup with read-query), post-steps (confirm_proposal), boundary conditions (which transaction types are excluded), and user interaction (relay preview). An agent can invoke it correctly without additional information.

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 100%, so the schema already documents both parameters. The description adds meaningful context by explaining how to obtain transactionId (via read-query, filtering) and its constraints, and by illustrating when to use editsProposalId. This goes beyond the schema's structural descriptions, though not to the level of exhaustive semantics.

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 opens with a specific verb and resource: 'Propose deleting an existing income or expense transaction.' It also differentiates from siblings by explicitly stating which transaction types are out of scope (transfers, buys, sells, IOUs) and directs the user to the appropriate pages, so an agent can distinguish it from other propose_* tools.

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 gives explicit when-to-use guidance: look up the target with the read-query tool first, pass its id, and call confirm_proposal with the returned proposalId after user approval. It also tells when not to use the tool (for transfers, buys, sells, IOUs) and provides the editsProposalId scenario for updating a pending proposal, leaving little to inference.

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