Journal Export

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

Annotations already provide readOnlyHint=true and openWorldHint=false. The description adds substantial behavioral detail: it is read-only, exports specific artifacts, includes a provenance probe toggle, and explains that a redacted journal exports an audit record rather than a runnable script. It also details the return structure for both listing and export modes. No contradiction with annotations, and the description enriches beyond the basic hints.

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 packed with information but every sentence earns its place. It starts with the core purpose, then explains parameters, redaction behavior, and return structure, all in a compact, organized way. There is no fluff or redundancy. It is dense yet readable, and the structure naturally leads from purpose to usage to output.

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 there is no output schema, the description includes a detailed return specification for both listing and export scenarios, covering fields like 'enabled', 'dir', 'live_session', 'sessions', and the export payload with 'warnings', 'integrity', 'provenance', etc. It also mentions configuration prerequisites (journal directory and redaction). Nothing critical for an agent to invoke the tool correctly is missing.

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 description coverage is 0%, meaning the schema only provides parameter names and defaults. The description compensates fully: 'session' is explained as an id or 'latest', with omitting it triggering listing; 'workspace' defaults to the one current when the session ended; 'provenance' defaults to true and can be set to false to skip solver version probes. All three parameters receive meaningful explanation beyond the 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 verb 'Export' with a specific resource ('past session from the on-disk journal'), and details the exact contents (replay script, environment, call ledger with SHA-256). It also explicitly references the sibling tool 'session_transcript' to distinguish itself, saying it exports 'as session_transcript would have' from the journal. This leaves no ambiguity about what the tool does.

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 provides clear context: it explains when listing occurs (session omitted) and the effect of the 'provenance' parameter. It references 'session_transcript' as a comparison point, implying a relationship, but it does not explicitly state when to use this tool over alternatives or when not to use it. There are no explicit exclusions or conditions beyond the journal being enabled. This is clear context without explicit when-not/alternative routing, hence a 4.

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