stop_recording

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently explains the side effects: the event log becomes annotations in the file, a metadata row is inserted by default, and raw crash-recovery files are normally removed after conversion. It also surfaces the register=false and keep_sidecar escape hatches, which reveals mutating behavior and cleanup semantics.

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 compact and front-loaded, with the primary purpose in the first line and supporting detail in a follow-up paragraph. Every sentence adds information that is not redundant with the schema — no filler, no repetition of parameter names without added meaning.

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 3 parameters (all documented), an output schema, and no nested objects, so complexity is moderate. With no annotations, the description must compensate, and it does a good job disclosing the primary side effects (file writing, metadata insertion, crash-file cleanup) and the register/keep_sidecar options. It doesn't enumerate potential failure conditions or what the output schema contains, but with an output schema present, return-value explanation isn't strictly required.

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%, so all three parameters are already described in the schema. The description adds contextual meaning beyond the schema by explaining what 'register' actually does (inserts a row with subject/task/run/provenance into the metadata store) and why keep_sidecar exists (raw crash-recovery files are normally removed). This adds real value over the bare schema.

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's verb (finish the recording), the resource (active recording session), and the specific actions performed: writing the .fif file and registering it for analysis. It distinguishes itself from siblings like stop_stream (which stops a data stream) and recover_recording (which handles crash recovery) by focusing on finalizing a recording into a file.

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 clearly says when this tool is used: to finish a recording session and produce a persistent .fif file for analysis. It explains the optional register=false path for skipping metadata insertion, giving the agent context on when to override the default. However, it doesn't explicitly name alternative tools or state when NOT to use it, though the sibling list makes this fairly evident.

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