mcp_agents_list

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

With no annotations, the description carries the full burden and does so: it discloses that unreachable agents are still returned (online=false), that online is derived from a live /hello probe, that the LAN is swept hourly automatically, and the time cost of a manual sweep. It also flags a security posture (default key) the agent should surface to the user.

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?

Front-loaded with purpose and return fields, then behavior, then the rescan caveat and the default-key advisory — logical ordering with no filler. The field enumeration is long but is load-bearing because there is no output schema; the only minor cost is that it reads as one dense paragraph.

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?

No output schema and no annotations, so the description compensates by enumerating every returned field including the timestamp format and semantics. Nothing an agent needs to call this correctly — caching behavior, sweep cost, unreachable entries, security prompt — is missing.

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 single parameter has 0% schema description coverage (a bare boolean), so the description must supply all meaning. It does: rescan triggers an immediate LAN sweep, is only warranted for hardware discovery, and costs 10+ seconds — far beyond what the schema conveys.

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?

Specific verb+resource ("List configured agents") with the domain scope enumerated (Pi, Pico, ESP32), and the returned fields named up front. It is trivially distinguishable from siblings like mcp_agent_restart, mcp_agent_upgrade, and mcp_agent_logs, which act on a single agent.

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 conditional guidance for the only optional parameter: pass rescan=true only when the user asks to find new hardware, with the cost stated ("a sweep takes 10 seconds or more"), implying the default path is a cheap cached read. It also gives a follow-up instruction when has_default_key is true.

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