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

The description discloses key behaviors beyond annotations: idempotent retries deliver only once, conflicts return without posting or charging, and quotas are enforced. Since annotations already declare idempotentHint=true, the description reinforces it and adds context about conflict behavior and quota enforcement, which is valuable. It does not contradict 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 compact, about three sentences, and front-loads the core action. Each sentence adds value: purpose, constraints, and conflict behavior. It avoids redundancy, though the last sentence about retries is somewhat tangential but still useful. No waste.

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 tool with 8 parameters and no output schema, the description explains the essential flow: what to provide (intro_id, own goal), how selection works (from discovery), and failure modes (conflict without posting). It does not detail ttl_hours or match_policy, but those are documented in the schema. Given the annotations cover idempotency and the description explains conflict behavior, it is sufficiently complete for an agent 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 description coverage is 50%, and the description adds meaning for two required parameters (intro_id, goal) by explaining their roles in the tool's purpose. However, it does not elaborate on optional parameters like match_policy, ttl_hours, or agent_key, which are left to the schema. Since the schema covers these sufficiently, a baseline 3 is appropriate.

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 specific action: reply to exactly one public request selected from discovery, requiring an intro_id and own goal/opening. It explicitly contrasts with peer instructions and distinguishes from the sibling tool speedbot_offer_intro by emphasizing 'not copied peer instructions' and selecting from discovery, making it unambiguous.

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?

The description provides clear conditions for use: targets are selected from discovery, and it specifies that stale, busy, incompatible, or same-swarm targets are rejected with a conflict. It also implies when not to use it (when you need to initiate rather than respond, use speedbot_offer_intro), but does not explicitly name alternatives or exclusion scenarios beyond those stated.

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