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

Annotations indicate destructiveHint=true, but the description adds useful non-obvious behaviors: it runs validation and returns the full result (row counts, warnings, blocking issues), never auto-applies mapping suggestions, and requires user-approved mappings. It also instructs reviewing warnings before ingesting. This goes beyond what annotations alone convey, though it doesn't explicitly describe side effects or what is destroyed.

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 three sentences, each earning its place: the first defines the action, the second states the return value, and the third provides a critical caveat. It is front-loaded with the main purpose and wastes no words.

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 tool has a nested `options` object and no output schema, the description does well to state the return value (full validation result with row counts, warnings, blocking issues). It also places the tool in the workflow ('staged upload', 'before ingesting'). However, it omits any explanation of the optional `options` parameters and `save_as`, which would be needed for full understanding of all inputs.

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 only 25% (only upload_id has a description). The description partially compensates by explaining that 'mapping' must be the exact mapping the user approved, and it references the upload_id as coming from a staged upload. However, the nested 'options' object and 'save_as' parameter remain completely unexplained, leaving a significant gap for a tool with four parameters.

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 specific action: 'Confirm the column→field mapping for a staged upload and run validation.' It names the exact resource (column→field mapping) and the verb (confirm/run validation), distinguishing it from sibling confirm_* tools that target other mappings (e.g., centre_mappings, groupings, reporting_lines).

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 contextual workflow guidance: 'for a staged upload' and 'before ingesting.' It also provides a key directive: 'Mapping suggestions are never auto-applied — pass exactly the mapping your user approved' and advises reviewing warnings before ingestion. While it doesn't explicitly compare to alternative tools, it clearly implies this is the step after upload_trial_balance and before ingest_upload.

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