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

Annotations already declare destructiveHint=true, so the agent knows this is a mutation. The description adds 'Add or update' but fails to disclose that account_name is 'fuzzy matched' (a serious risk for unintended writes) or whether an existing note is overwritten or appended. The empty-string-to-clear behavior is only in the schema, not the description, leaving behavioral gaps beyond annotation coverage.

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 two core sentences are efficient and front-loaded, but the appended write-tier approval block is verbose and tangential to the tool's function. It includes operational guidance (from-now-on vs just-once, 'card is the yes') that could be condensed. Overall, the description is longer than necessary due to the approval section.

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 destructive finance tool with no output schema, the description is incomplete. It omits critical details such as the fuzzy-matching risk for account_name, whether the note replaces or appends, and what happens when the account is not found. While the approval instructions are present, they address workflow permissions rather than tool behavior, leaving an agent under-equipped to call this safely.

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 description coverage is 100%, so each parameter already has a clear description (e.g., 'fuzzy matched', 'empty string to clear'). The description adds illustrative note content but no additional semantic meaning beyond the schema. Baseline of 3 is appropriate because the schema carries the full parameter documentation burden.

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 clearly states the tool 'Add or update a note on a P&L account row' with concrete use examples ('Includes annual contract renewal'). It names the specific resource (P&L account row) and action, making the purpose unambiguous. It does not explicitly contrast with sibling tools like update_transaction_note, so it loses a point for lack of differentiation.

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 a general use case ('Use this to annotate accounts with context') but no guidance on when to choose this over alternatives (e.g., update_transaction_note). The approval-flow note ('Call it on the first clear ask') addresses invocation timing, not tool selection. An agent receives no exclusions or alternative routing, leaving selection to inference.

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