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

The description declares '(READ-ONLY: mutations refused)' while the annotations declare readOnlyHint=false, i.e. this tool is not a pure read. Signing and journaling are inherently write operations, so the stated read-only guarantee directly conflicts with the structured safety metadata, leaving the agent unable to know whether calling it changes state.

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?

Front-loaded with the action and resource in a single dense sentence, with the outcome enum values inline for quick scanning. The trailing parenthetical is short but misleading rather than wasteful, so it loses a point for content quality, not length.

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?

A 6-parameter mutation tool with no output schema needs to say what it writes, where, whether it requires a prior dispatched receipt, and whether repeated calls are safe. Only the outcome values and the learning-loop intent are covered, and the contradictory read-only claim actively misleads about side effects.

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 67%, so the schema already documents most parameters. The description echoes the outcome values (success, failure, corrected) but omits 'unknown', and says nothing about receipt_path format, corrected_route semantics, or what tenant_id/session_id scope. Marginal value over 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 names a specific verb pair (sign and journal) and a specific resource (the outcome of a dispatched decision/shortlist receipt), and lists the outcome values it accepts. It implicitly distinguishes itself from decision.deliberate and decision.shortlist by operating on an already-dispatched receipt, though it never names those siblings explicitly.

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?

It gives a purpose context ('for the learning loop') and implies you call it after a decision has been dispatched, but it never states preconditions (must a receipt exist first?), when not to call it, or which sibling to use instead for other decision lifecycle steps. Usage is inferable but not spelled out.

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