Narrate a live set (persisted decision log)

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

Annotations already set readOnlyHint=false and destructiveHint=false, and the description adds concrete behavioral detail: 'Writes a local file (not read-only)' and explains append is timestamped and recall reads the last `tail` lines. This goes beyond the annotations by specifying the side effect (local markdown file) and append-only nature, though it doesn't discuss permissions or error handling.

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 sentences cover purpose, modes, usage context, and sibling distinction with zero filler. The most important information (persist narration) is front-loaded, and every sentence adds value.

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?

Given the tool's moderate complexity (7 parameters, two modes, file I/O), the description covers the essential context: what it does, when to use it, how modes behave, and how it differs from log_performance. The output schema and parameter descriptions fill in remaining details, so the description is fully adequate.

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 the baseline is 3, but the description adds meaning by explaining how mode='append' and mode='recall' use parameters like section, cue, and tail. It also clarifies the default log path behavior (date-based set_name), enriching the schema's parameter descriptions.

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 opens with a specific verb+resource: 'Persist the running narration of a live VJ/show set so decisions can be recalled afterwards.' It then clearly distinguishes the two modes (append and recall) and explicitly contrasts with the sibling tool log_performance, removing any ambiguity about its purpose.

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 gives explicit usage guidance: 'Pair with the auto_vj_director prompt: instead of narrating only in chat, call narrate_set on each major move.' It also provides a clear alternative: 'Delta vs log_performance, which writes a one-shot network snapshot rather than an append-only decision log,' telling the agent when to use this tool versus log_performance.

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