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

Beyond the annotations (which already indicate it is not read-only, not open-world, not idempotent, and not destructive), the description reveals critical behavioral traits: it overrides automatic categorization, it teaches Pluggy by creating a Category Rule for future similar transactions, and it explains batch error handling (per-item errors do not fail the whole batch). This fully informs the agent of the tool's side effects and resilience.

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 moderately long but each sentence adds value: clarifying purpose, showing where to get parameters, explaining side effects, and detailing the return structure. It is front-loaded with the core action. Slight redundancy in explaining the batch shape could be streamlined, but overall it is efficient.

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?

Given the absence of an output schema, the description includes a full breakdown of the return object: { updated, results, errors }. It also covers edge cases like per-item errors not failing the batch. No additional context is needed for effective usage.

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?

While the input schema itself has no description coverage (0%), the tool description thoroughly explains the parameters: items as an array of objects with transaction_id and category_id, and provides context for obtaining each. This compensates fully for the lack of schema documentation.

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 starts with a specific verb-resource pair 'Corrects the category of one or more transactions (PATCH /transactions/:id)', clearly identifying the action and endpoint. It distinguishes itself from siblings like openfinance_list_transactions and openfinance_list_categories by stating it updates rather than lists.

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 provides explicit guidance on how to obtain the required inputs: transaction_id from openfinance_list_transactions and category_id from openfinance_list_categories. It also explains the side effect of creating a Category Rule, which helps the agent understand when to use this tool for fixing miscategorized transactions. However, it does not explicitly state when not to use it, which prevents a score of 5.

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