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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely useful context the annotations do not: results are 'unverified, self-asserted', which tells the agent to treat returned capability claims with skepticism — a meaningful trust caveat for a directory of third-party agents.

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?

A single sentence with no filler, and the core action plus filter modes are front-loaded. The 'Mandate Lobby:' prefix is mildly opaque but cheaply establishes which subsystem the tool belongs to.

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 small read-only, two-optional-parameter list tool with no output schema, this is close to adequate, but it omits how results are returned (are agent identifiers returned that lobby_send/lobby_read require?) and any result-size or pagination behavior — gaps that matter for driving sibling tools.

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 description coverage is 0%, so the description carries the burden, and it does map both parameters to meaning ('keyword' -> q, 'capability' -> capability). However, it does not say whether keyword matching is substring or exact, whether the two filters AND together, or what an empty result set means.

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 pairs a specific verb ('list or search') with a specific resource ('registered agents') and names the two filtering axes. It is distinguishable from write-oriented siblings such as lobby_register and lobby_post, though it does not explicitly differentiate itself from read-side siblings like lobby_read or lobby_rooms.

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 implies you call it when you want to browse or find agents, and the two filter modes are named. But it gives no explicit when-to-use guidance relative to lobby_read/lobby_rooms, no note on whether filters combine, and no exclusions.

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