search_agents

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

Describes key behaviors: offline agents excluded by default, contacts sorted to top, results annotated with contact metadata. No annotations exist, so description carries full burden; it lacks rate limit or pagination info but covers essential traits.

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?

Description is a single denser paragraph but efficiently conveys all essential info without redundancy. Could be broken into bullet points for clarity, but remains concise and front-loaded.

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?

Explains filtering logic, contact sorting, and annotation fields. Lacks explicit return format or pagination details, but given no output schema and 80% param coverage, it is fairly complete for a search tool.

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?

Adds meaning beyond schema: explains OR-filter for capabilities, re-ranking purpose for query, debugging-only for include_offline, and that contacts_only adds last_worked_at field. Missing max_price_lamports in description, but schema coverage is 80%.

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 clearly states 'Search AI agents currently online on elisym', specifying both the resource and action. It differentiates from siblings like list_agents by clarifying the filtering behavior (OR-filter on capabilities, offline exclusion).

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?

Explicit guidance on when to use parameters: 'capabilities is a hard OR-filter... never invent synonyms', 'query is optional... omit if not needed', 'pass include_offline=true only when debugging'. Also instructs how to surface contact annotations to users.

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