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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new behavior: write capabilities are rejected with a pointer to the local router, the response is a verifiable TRACE Receipt with a reproducible sha256 commitment, and duplicate execution is prevented by the idempotency key. It does not contradict any annotation.

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?

Three tight sentences, front-loaded with the action and result before the constraints. Dense jargon ("TRACE Receipt", "canonical output") is used purposefully but slightly reduces first-pass readability.

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?

With no output schema, the description carries the burden of explaining the return artifact and does so. For a tool with a nested free-form input object, it still leaves capability_id and the discovery path to get_capability implicit, but overall an agent has enough to call it correctly.

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 75%, so most parameters are already documented; the description mainly reinforces idempotency_key, adding the rationale "so retries never double-execute" and the 8-128 char range already present in the schema. capability_id remains undocumented in both places, and quote_id/input are left entirely to 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?

Opens with a specific verb+resource ("Executes a free read") and immediately characterizes the result (a TRACE Receipt binding request, terms, outcome and evidence with a sha256 commitment). This distinguishes it cleanly from siblings like get_capability (describes) and get_execution (retrieves past runs) without needing their schemas.

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?

Gives an explicit when-not: write-capable capabilities are refused here and routed to the local router. It also tells the caller to supply an idempotency_key for retries. It does not explicitly say to call get_capability first to obtain the input schema (that hint lives only in the schema), so routing among siblings is implied rather than stated.

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