discover_peers

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

Annotations already mark readOnly=truehol, and the description adds key behavioral facts: it relies on the enrolled device identity and requires enrollment, and explicitly states no codename is needed. This goes beyond the annotation by clarifying a prerequisite and identity source, though it does not discuss side effects (which are minimal for a read operation).

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?

Well-structured with clear numbered categories and a usage note, but slightly longer than necessary. Each section adds content (mentor/peer/complementary explanations), yet the level of detail could be trimmed without losing meaning. Still earns credit for front-loading the core purpose and providing terse category definitions.

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 (three output categories, identity-based logic), the description is thorough: it explains the rank-tier logic, what each category contains, the enrollment dependency, and returns are implied by the description. This covers all aspects an agent needs to invoke it correctly, and the output schema can handle details.

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 descriptions already fully cover both parameters (n with default/range, platform with default behavior). The description adds that the operator's identity is auto-detected, but this is context for the overall tool, not a parameter-specific clarification. Since schema coverage is 100%, baseline is 3; no extra value is added.

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?

Clear, specific verb ('discovers') and resource ('mentors, peers, and complementary operators on the SigRank leaderboard'), with three enumerated categories that sharply distinguish from sibling tools like rank_paste or diagnose_cascade. Scope is explicit and 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?

Provides explicit when-to-use instruction ('after submit_verification') and a recommended follow-up chain ('then chain into self_improvement with the mentor's pillar deltas as context'). This gives the agent a concrete decision path and eliminates guesswork about tool ordering.

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