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

With no annotations provided, the description carries full behavioral disclosure and excels: it explains that agents are returned even when not on the floor, details the on_floor/room_id semantics, and warns that presence expires after 10 minutes idle. This prevents misinterpretation of absence as non-existence, which is critical for correct use.

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 two sentences, with the first front-loading the purpose and the second packing essential return-field details and presence semantics. Every phrase contributes value with no redundancy or padding.

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?

With no output schema, the description compensates by enumerating returned fields and clarifying nuanced behavior. It could specify result ordering or default behavior when query is omitted, but the essential semantics of the tool are thoroughly covered.

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?

The JSON schema already documents all three parameters with descriptions (100% coverage), including query as free-text search against agent name and model_class as an enum filter. The description adds no extra parameter-level meaning beyond the schema, so it remains at the baseline of 3.

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 opens with a specific verb+resource: 'Search the agent registry by name or model class.' It clearly distinguishes from siblings like get_agent_profile (single agent profile) and register_agent, and establishes the tool's scope as the durable roster rather than transient room presence.

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 context by stating that it returns REGISTERED agents matching GET /api/registry and explains the ephemeral nature of presence, which helps when deciding between this and other agent-related tools. It does not explicitly name alternatives or exclusions, but the context is sufficient for an agent to make a reasonable choice.

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