gc_relay

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

No annotations are provided, so the description carries the full behavioral disclosure burden. It does disclose that this is a 'relay ingress' that sends messages and can create new sessions, and mentions the daemon-owned default agent (charon). However, it does not disclose any side effects of creating a session, whether operations are reversible, permission requirements, or what happens when a session already exists with a given session_id. Moderate disclosure but gaps remain for a message-mutation tool.

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?

Two sentences, tight and efficient. Covers purpose, behavior (send vs create), and the default agent. No waste, though it could arguably add more params explanation without hurting brevity.

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?

Schema covers all 4 params at 100%, so parameter documentation is complete. However, no annotations and no output schema means the description should carry more runtime behavior context. It does not explain the relationship between session_id and config (e.g., config only applies when creating), nor what the response contains or failure modes. For a tool that mutates state by creating sessions, this is a partial gap.

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 description coverage is 100%, so baseline is 3. The description adds 'default charon' context that clarifies the agent param's default, and notes sessions can be created vs. reused which maps to session_id/config semantics. It adds marginal value beyond the schema, particularly the charon default which is genuinely helpful.

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 a specific verb+resource: 'Relay ingress for external peers... Sends a message to an existing agent session or creates a new one.' This distinguishes the tool from siblings like gc_recall, gc_retain, and gc_reflect (which are clearly different operations). The mention of Pluto as an example external peer adds concrete context. Well-scoped and specific.

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?

No direct sibling differentiation is given - it doesn't say 'use this instead of X' or 'when not to use'. However, the phrase 'for external peers' establishes a clear intended context, and the distinction between send-to-existing and create-new is implicit guidance. It lacks explicit exclusion context or alternative tool mentions, which matters given the large sibling list.

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