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

The description discloses important behavioral traits beyond annotations, such as bearer token resolution per role ('Bearer resolves per-role... never passed via this tool's prompt surface'), auto-fill of 'sender' and 'role' from session context, and the fact that 'status' is a diagnostic with no server call. It also explains the authentication mechanism, which is not covered by annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false). This adds valuable context for safe usage.

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 well-structured with clear action headers and bullet-like formatting, making it easy to scan. It front-loads the overall purpose and then details each action concisely. Each sentence adds value, covering return shapes and optional fields without excessive verbosity.

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 the tool's complexity (multiple actions, authentication, env vars), the description covers the essential aspects: actions, parameters, return values, and auth mechanism. However, it lacks mention of error handling beyond the optional 'error' field, rate limits, or the relationship to sibling tools like 'nucleus_relay_subscribe'. The agent may need additional context for robust usage.

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 description provides detailed parameter semantics for each action, compensating for the input schema which has 0% description coverage. For example, it lists all parameters for 'post' (to, subject, body, sender?, priority?, in_reply_to?, context?, id?, from_session_id?) and explains aliases and auto-fill behavior. However, not all parameters (e.g., 'priority', 'context') are explained in depth, leaving some ambiguity.

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 clearly states the tool is a 'Relay-substrate facade' with actions 'post / read / ack / status', identifying its core purpose of relay messaging. It lists specific actions like 'send a relay envelope' and 'list inbox messages', making the purpose distinct. However, it does not explicitly differentiate from the sibling tool 'nucleus_relay_subscribe', which could cause ambiguity for an AI agent.

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?

There is no explicit guidance on when to use this tool versus alternatives like 'nucleus_relay_subscribe'. The description focuses on how each action works but does not provide context about when to choose this tool over others. An AI agent would need to infer usage from the action names alone, lacking clear decision criteria.

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