pilot_send

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

No annotations are present, so the description carries full responsibility. It discloses the critical behavioral trait that trust is required, states that send 'WILL fail with a connection error' for untrusted or one-way states, and tells where replies land ('pilot_inbox'). This goes beyond a generic send operation and reveals failure modes and async behavior.

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 three sentences, front-loaded with the main action, then the key exclusion, then the trust prerequisite and reply behavior. Every sentence adds distinct value with zero fluff or repetition. It is rich but compact.

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?

For a messaging tool with a trust prerequisite and potential failure modes, the description covers the action, target, message format, preconditions, failure behavior, and reply location. It also names alternatives appropriately. No output schema exists, but the description tells where the reply goes, which is sufficient for the agent to use the tool 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 100% with descriptions for all three parameters, so the baseline is 3. The description adds important semantic context beyond the schema: it emphasizes that 'message' expects natural language rather than /data commands, and that the peer should be a 'known peer'. It also connects wait_seconds to the reply destination via pilot_inbox, enhancing understanding.

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 sends a plain-text message to a known peer, using a specific verb and resource. It explicitly distinguishes from directory specialists and other sibling tools by saying 'NOT a directory specialist' and 'Use this for A2A messages to human-operated agents and bespoke peers.'

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?

Provides explicit when-to-use guidance: 'Use this for A2A messages to human-operated agents and bespoke peers.' It also names exclusions and alternatives: directory specialists need pilot_search/pilot_help/pilot_query for the /data verb pattern. Additionally, it gives a mandatory prerequisite: call pilot_trust_check(target) first, with clear failure consequences.

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