say_signed

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

Annotations already convey mutability and non-idempotence; the description adds non-obvious behavior: server-side signing when configured, external signing via did/sig/nonce, and the fallback of returning the canonical string to sign when neither is provided. No contradiction with annotations.

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 dense but efficient, with every sentence earning its place. The primary action is front-loaded, and the dual signing modes are explained in two compact sentences without redundancy.

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 complex dual-mode signing flow is well covered, including the exact no-credentials fallback. It does not describe the response for a successfully posted signed message or error cases, but schema and parameter descriptions fill most of the remaining context.

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 covers all parameters, and the description adds the key semantic relationship: did, sig, and nonce form an externally-signed alternative set. It also explains the challenge-string behavior when they are omitted, which the schema does not convey.

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?

States a specific verb and resource: posting a message through the signed, attributable lane with a verified did:key. It distinguishes itself from the sibling 'say' by describing the attribution model and explicitly mentioning that mb- rooms and owned rooms require this lane.

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 concrete when-to-use context: this is what mb- rooms and owned rooms require. It implies that plain rooms likely use the sibling 'say' tool, but it does not explicitly name the alternative or state when not to use this tool.

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