replace_submission_files

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description's 'replaces' aligns with those. The description adds useful context beyond annotations: it specifies that the replacement is of the *exact* set of files previously confirmed, which clarifies that the operation overwrites the entire submission file set rather than incrementally updating. It also hints at a needed confirmation step (confirmation_token). However, it doesn't detail consequences like whether old files are permanently lost, or whether the operation is reversible, so it partially leverages the annotation coverage but doesn't fully expand on behavioral traits.

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 a single concise sentence in Spanish, which is efficient and easy to parse. It is front-loaded with the main action and object. There is no fluff or redundancy, and it fits the expected pattern for a tool description. Slightly higher would require providing more structure (like separating purpose from usage), but for what it is, it's well-shaped.

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?

The tool has three required parameters, a destructive action, and no output schema, so the description carries a heavy burden. It only states the high-level action and the 'exact set' constraint, but it omits critical details: what constitutes a valid file path, how the confirmation_token is obtained or validated, whether there are constraints on assignment_id, and what the response indicates (success, errors, etc.). The presence of a preview tool (preview_replace_submission_files) suggests a workflow, but this description doesn't connect to it. For an agent to call this correctly, far more context is needed.

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 0%, meaning the description must compensate by explaining the parameters. It does not: file_paths, assignment_id, and confirmation_token are never mentioned or elaborated. The phrase 'previously confirmed' loosely alludes to the confirmation_token, but it doesn't name it or explain how to obtain it. The description adds zero value for parameter understanding, leaving the agent reliant on parameter names alone for 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 clearly states the action ('Sube y reemplaza' – uploads and replaces) and the resource ('el conjunto de archivos exacto previamente confirmado' – the exact set of files previously confirmed). It distinguishes from siblings like preview_replace_submission_files (which previews) and delete_submission_files (which deletes) by focusing on replacement, and the 'previously confirmed' qualifier adds specificity. However, it doesn't explicitly name alternative tools or edge cases, so it's not a perfect 5.

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 no guidance on when to use this tool versus alternatives. It does not mention prerequisites, such as obtaining a confirmation_token from a prior step, nor does it reference the preview tool (preview_replace_submission_files) as a recommended precursor. Without any context on when this is the right choice (e.g., 'after previewing with preview_replace_submission_files'), an agent has to infer usage from the name and schema. This is a significant gap.

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