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

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint, but the description goes well beyond those: it warns that 'include_rationale' opts journal rationale and intended action into the public card, stresses that journal body is private and publishing is an explicit act, explains that the card deliberately excludes amounts and percentages, and details the CRAFT record fields and Explorer link. This gives the agent a strong behavioral model beyond the structured annotation data.

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 organized with useful sections and front-loading, but it is verbose and includes rhetorical framing like 'Every trading claim online is an unverifiable screenshot,' which does not earn its place for tool invocation. The privacy note and workflow are valuable and the structure is readable, but it should be tighter.

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 an output schema, the description does not need to explain return values, and it provides strong context for behavior, privacy, and workflow. What keeps it from a 5 is that the workflow refers to a sibling tool and the parameter semantics are incomplete, so an agent still has ambiguity about what fields are necessary and how the card is surfaced relative to 'share_journal_card'.

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 has 0% property description coverage, so the description must carry parameter meaning. The only parameter actually explained in the description is 'include_rationale,' including its default and privacy consequence. The other three parameters — 'wallet_address', 'decision_id', and 'caller_id' — receive no meaningful explanation or format guidance, which is a significant gap for a tool with zero schema 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 states a clear verb and resource: 'Build the shareable journal card for one of YOUR decisions.' It also adds limiting context like 'free read' and 'no amounts and no percentages,' which clarifies the intent. However, it does not explicitly differentiate the tool from the sibling 'share_journal_card' and actually names that sibling in its workflow, so the agent cannot be fully certain where the boundary between 'get' and 'share' is.

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 some usable context: it should be used after 'journal_append / journal_query,' and the resulting card is a process record rather than a claim about results. But it does not explicitly say when not to use the tool, and the workflow sentence says 'then share_journal_card to get the pre-filled post,' which appears to point at a sibling instead of the tool itself. This makes the usage guidance ambiguous.

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