record_decisions

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

No annotations, so the description must carry behavior and it mostly does: it discloses the keying strategy (video path + file size, not session), the persistence behavior across ui-state.json overwrites, and the partial-update merge semantics. It doesn't cover permissions or failure modes, but the core behavioral traits are unusually well disclosed.

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?

Three dense but purposeful sentences, front-loaded with the purpose before the keying and partial-update mechanics. No obvious filler, though the parenthetical field list is long.

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 10-param mutation tool with no annotations and no output schema, the description covers purpose, persistence model, update semantics, and a sibling pointer. The main omission is what the call returns and any permission requirements.

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 80%, so most parameters are already documented. The description lists the categories of decisions but adds little per-parameter meaning beyond the schema, which already describes fields like video_path, clip_count, and notes. Baseline 3 is appropriate.

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?

States a specific verb (record) and resource (per-episode workflow decisions), then enumerates exactly which decision fields are covered. It distinguishes itself from siblings like get_ui_state by naming it as the read counterpart.

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?

Explains the why (so later runs never re-ask) and the interaction model (pass only fields you have; existing answers preserved). It routes to get_ui_state for unanswered fields. It does not explicitly say when not to use it, but the context is clear.

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