agent_presence

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

Annotations declare readOnlyHint=false and openWorldHint=false, so the mutating-but-local nature is already signaled; the description usefully adds that the server mints a UUID/key and short name on first call, that later calls are refreshes, and that the granted name carries no filesystem/command permission. It does not mention rate limits, idempotency, or what happens on credential mismatch, which keeps it out of 5 territory.

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?

Four short sentences, front-loaded with what the tool does and immediately followed by the credential lifecycle, which is the most decision-relevant fact. Slight redundancy between 'No model/name handshake question is needed' and the schema's 'no extra handshake' note, but nothing is wasted overall.

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 14-parameter, no-output-schema, nested-object tool the description covers the lifecycle and the shape of the first-call return value well. It still leaves most parameter semantics and the effect of 'stopped' undefined, which is a real gap even accounting for the credential explanation.

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 only 14% across 14 parameters, so the description must carry the load, yet it only glosses activity/project/task/model/phase and omits runtimeId/runtimeKey, stopped, source, capabilities, label, node, and includeHostMemory. Even the hinted fields get no format or constraint detail beyond what the schema enforces.

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?

Names a specific verb pair (announce/refresh) and a specific resource (this AI runtime's activity, project/task, model, phase), so it is clearly distinct from siblings like agent_monitor and agent_message. It never names a sibling explicitly, so it stops short of a 5, but an agent can place it correctly.

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?

Gives clear lifecycle context: the first call obtains server-issued credentials, later calls reuse them, and no separate model/name handshake is required. That answers the main 'when do I call this' question, but there is no explicit exclusion or pointer to an alternative tool for presence queries.

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