tsf_export_run

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

Annotations already indicate readOnlyHint=false and destructiveHint=false. The description adds valuable context: 'Writes a file, so it is not read-only' and lists everything included in the manifest. It also emphasizes that the note is the only place a reasoning trace survives, which is important behavioral insight. No contradictions with annotations.

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 well-structured: starts with the core purpose, then enumerates contents, gives usage advice, and closes with a note about file writing. It is not overly long; every sentence contributes. A slight trim could improve conciseness, but it remains clear and front-loaded.

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 that an output schema exists, the description correctly omits return value details. It covers when to call, what the manifest contains, and the critical role of the note. The only minor gap is no mention of potential side effects (e.g., overwriting existing files), but overall it is sufficiently complete for a tool with good annotations and schema.

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 input schema already contains descriptions for both parameters: handle ('Handle whose run log should be pinned to a manifest') and note (detailed explanation of what to write). The tool description adds further guidance for the note, specifically: 'Write the note -- say which model you picked, what the metric table showed, and what you rejected.' This enhances the schema's descriptions, making it clear how to use the note parameter effectively.

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 opening sentence 'Write a JSON manifest of everything done to this handle' clearly states the verb (write a manifest) and the resource (handle). The description further details what the manifest includes (source path, SHA-256, calls, arguments, artifact paths, pinned package versions, note), differentiating it from sibling tools like 'tsf_export_report' or 'tsf_describe_series'. This makes the tool's purpose unmistakable.

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 tells when to call it: 'Call it at the end of any analysis someone might have to defend or rerun.' This provides clear context for use. It does not explicitly state when not to use it or name alternatives, but for a specialized export tool the guidance is sufficient and well-placed.

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