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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false. The description adds genuinely useful context beyond these: it is a non-committing draft producer, enumerates the returned fields, and states the confirmation:true requirement and the account-omission defaulting behavior. It does not cover latency/cost of vision extraction, keeping it below a 5.

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?

Front-loaded with what the tool does and the critical 'NOT committed' caveat up front. Dense but nearly every sentence carries actionable information; only the account-defaulting sentence mildly duplicates the schema.

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?

With no output schema, the description compensates by enumerating returned fields (amount, date, description, type, suggestedCategory, suggestedAccountId). Together with the workflow guidance and confirmation requirement, an agent has everything needed to call it and act on the result.

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 parameters are already fully documented. The description's note about accountId omission (currency defaults to USD, suggestedAccountId null) largely restates the schema's own accountId description rather than adding new semantics. Baseline 3 is appropriate.

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?

States a specific verb and resource: runs AI vision extraction on a base64 receipt/PDF and returns a PREFILLED draft, explicitly 'NOT committed'. This clearly distinguishes it from the sibling add_transaction, which it names as the follow-up persistence step.

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?

Explicit two-phase workflow: this tool produces a reviewable draft, then the agent should call add_transaction or bulk_add_transactions to persist. Also flags a branching condition (if accountId omitted, agent must choose an account before committing).

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