discover_agents

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

With no annotations provided, the description carries full burden and delivers: states it's a pure read ('never mutates last_seen'), explains the difference between computed `status` vs operator-controlled `agent_status`, discloses token hashes are stripped (returns `has_token: boolean` only), documents the exact return shape, ordering, and error mode (RATE_LIMITED), plus the notable detail that no auth is required for observability. This is remarkably complete behavioral disclosure.

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-organized with clear section labels (When to use, Behavior, Returns, Errors), front-loaded with the core purpose sentence. Every sentence earns its place. Slightly dense in the Behavior section covering multiple concepts, but the structure is clean and scannable, so only a minor deduction.

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 read-only list tool with zero required params and 100% schema coverage, the description is exceptionally thorough: it documents return shape, ordering, error modes, auth posture, security behavior (token stripping), and the semantic distinction between computed vs operator-controlled status fields. Despite no output schema, the description fully compensates by spelling out the response contract.

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%, so baseline is 3. The description adds value on top: explains that `role` is an optional filter, clarifies that `status` is computed while `agent_status` is operator-controlled (differentiating the semantics of what the tool returns). Since all params are already fully documented in the schema at 100% coverage, the description's contributions are bonus context rather than compensation.

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?

Description states the exact verb+resource ('List every registered agent with computed presence + operator-controlled status'), explicitly distinguishes from sibling `get_standup` by naming it and contrasting scope. The phrase 'list every registered agent' with the added detail of computed presence and operator-controlled status makes the purpose concrete and non-tautological.

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 with three concrete scenarios (routing target by role, confirming online before sending work, surfacing fleet to dashboard) and an explicit exclusion ('use get_standup instead, it bundles agents + recent activity'). This is textbook usage guidance with clear when-to and when-not-to direction.

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