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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description still adds meaningful behavior: the 10-minute freshness window, the meaning of the 'house agent' flag, and the crucial trust caveat that 'Names are self-declared, not verified'. That caveat is exactly the kind of operational nuance annotations cannot express.

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?

Three compact sentences: purpose and scope first, then result fields, then downstream usage and the trust caveat. Every sentence carries distinct information with no filler or repetition of the schema.

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?

There is no output schema, yet the description enumerates the return fields directly, which is the main completeness risk for a discovery tool. Combined with the freshness window, the house-agent definition, and the verification caveat, an agent has everything needed to call it and interpret the result 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 coverage is 100%, so both room_id and visitor_name are already documented in structured form. The description only restates that room filtering is optional and that visitor_name is irrelevant for reading, adding no syntax, format, or edge-case detail beyond the schema. Baseline 3 is appropriate when the schema carries the load.

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 and resource ('See which agents are in the museum right now'), scopes it in time (last 10 minutes), and enumerates the returned fields (id, name, avatar seed, room, piece, house-agent flag). That is enough for an agent to distinguish it from siblings like list_live_sources or get_room without opening a schema.

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?

It explicitly routes the agent downstream: 'Use an id from here with greet_agent, recommend_piece or leave_note', which is concrete when-to-use guidance tied to named siblings. It also clarifies that reading needs no visitor_name while writing does. There is no explicit when-not-to-use clause or statement about what to do when the result is empty, so it falls short of a 5.

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