recover_recording

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

The description transparently discloses a critical limitation: events are not recoverable since they lived in memory, so the output file has signal without annotations. This is valuable behavioral context beyond any annotation. However, with no annotations at all, the description carries full burden and could also mention success criteria or failure modes, keeping it just below 5.

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 tightly organized: opening verb statement, mechanism explanation, usage instruction, and limitation note. Every sentence earns its place with no filler or redundancy. Fairly compact for the depth it provides.

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?

There is an output schema present, so return-value explanation is not needed. The description covers the recovery mechanism, the target artifact, and the key loss tradeoff. The only minor gap is no explicit mention of whether the original header remains intact or is consumed, but given the output schema and solid prose this is quite complete.

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 100%, with header_path and keep_sidecar both described in the schema. The description adds context on header_path by calling it an 'orphaned' file and clarifying its role, which adds meaning beyond the schema. With full schema coverage, baseline is 3, and the description's nuance on the header file bumps it to 4.

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 tool recovers an interrupted recording by converting an orphaned header file to a .fif. It uses specific verbs ('finish', 'convert') and names the resource (.eegmcp.json header). It effectively distinguishes from siblings like start_recording/stop_recording by addressing the failure-recovery niche.

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 explicitly explains when to use this: when a recording process died before closing, point it at the orphaned .eegmcp.json header. It provides concrete context ('Samples are appended to disk as they arrive and the header is written up front') that clarifies the scenario this tool is designed for and implies it is not for normal recording closure.

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