Prune Commits

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

With no annotations, the description carries the full burden. It discloses the core destructive behavior (purge) and the conditional protection of pinned baselines, but it does not clarify the selection algorithm for enforcing max_size_mb (e.g., which snapshots are deleted if none are expired) or state that deletion is irreversible. This ambiguity is significant for a destructive tool.

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 two sentences with no filler. It front-loads the core purpose and then adds a precise condition, making every word count.

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 3-parameter tool with an output schema, the description covers the main function and parameter roles adequately. However, the underspecified size-overshoot deletion behavior leaves an agent unable to fully predict consequences, and the presence of an output schema does not compensate for that behavioral gap. Overall, the description is usable but not fully complete for a destructive operation.

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%, yet the description gives functional meaning to all three parameters: ttl_days relates to TTL-based expiry, max_size_mb to the size cap, and keep_baselines to the protection of pinned baselines. It stops short of explicitly defining TTL in days or the exact behavior when keep_baselines=false, but it provides enough context for an agent to understand parameter roles.

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 states a specific verb ('Purge') and resource ('les snapshots expirés') with distinct mechanisms (TTL and max_size_mb). It also mentions conditional protection of pinned baselines, clearly differentiating it from sibling tools like list_commits or restore_commit.

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 implies usage for cleanup tasks (pruning expired snapshots and enforcing size limits), but it does not explicitly state when to use this tool vs. alternatives or any exclusions. An agent must infer the intended context from the purpose rather than receiving direct guidance.

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