journal

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

With readOnlyHint=true, the safe-read nature is already annotated. The description adds meaningful context about what the journal contains, what it excludes, and the audit/replay use case, going beyond the annotation's bare safety signal.

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 two tight sentences: the first states the core function and contents, the second gives usage guidance and an exclusion. Every sentence earns its place with no filler.

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 is simple, the schema is complete, and the read-only annotation covers safety. The description explains the return content, use cases, and exclusions, so an agent has enough context to select and invoke the tool correctly without an output 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 schema describes both parameters fully, including default values, constraints, and field-specific semantics, so schema coverage is 100%. The description adds no additional parameter-level detail, which fits the baseline 3 for high schema coverage.

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 states a specific verb and resource: 'Read back the trail of acted tool calls.' It also clarifies scope and content by listing what is journaled (arguments, outcome, hit/miss verdict, screenshot hash) and distinguishes itself from sibling tools with 'Reading tools are not in it.'

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 use cases: reconstruct past context after loss and review an unattended run. It also provides a when-not-to-use signal by stating that reading tools are not included, though it does not name specific alternative sibling tools.

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