cleanup_captures

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

With no annotations, the description carries the full behavioral burden. It does disclose two genuinely useful traits: deletion is immediate (irreversible, bulk-wide) and it explicitly does not stop the TTL sweeper, which corrects a likely misconception. However, it says nothing about permissions required, whether in-flight capture operations are affected, or what the returned output reports.

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?

A single sentence with the destructive scope front-loaded, and the parenthetical caveat about the TTL sweeper earns its place by preventing a specific wrong assumption. No wasted 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?

The output schema is available so return values need no explanation, and the zero-parameter schema is trivial. For a destructive, unannotated operation the description is nearly sufficient, with the only real gap being the absence of any confirmation or permission caveat before an irreversible bulk delete.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies.

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?

"Immediately delete all session captures" names a specific verb (delete) and a specific resource (all session captures), which cleanly separates it from the read-oriented siblings list_captures and capture_window. It stops short of naming a sibling or clarifying its relationship to capture_monitor, so it stays at 4 rather than 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?

There is no explicit guidance on when to call this versus the capture_* or list_* tools. The name 'cleanup' implies a housekeeping use case, but the description never states an intended scenario, precondition, or exclusion.

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