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

Annotations already declare readOnlyHint=true, destructiveHint=false, so safety is covered; the description still adds real value by disclosing the shape of the response (instance fields id/name/owner/status/liveness/credentials, plus a token page and pagination). It does not mention auth/permission requirements or error behavior, which keeps it short of a 5.

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 front-loaded sentence opening with the verb and resource, then the return payload, then the cross-tool payoff. No filler clauses; every segment carries information.

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 and six parameters, the description carries the return-value burden and does so by listing instance fields and the token page. Token fields themselves are only summarized ("provisioner tokens"), a minor gap in an otherwise complete definition.

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 each parameter (slug, instance_q, offsets, statuses) is already documented with page-size context. The description reinforces the paging model ("a page of its instances") and explains the downstream significance of the returned ids, but adds no syntax or semantics the schema lacks — baseline 3 fits.

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?

States a specific verb and resource ("Read one agent") and enumerates exactly what it returns: kind, status, a page of instances with named fields, and a page of provisioner tokens. The singular "one agent" cleanly separates it from the sibling list_agents without either schema being opened.

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?

Explicitly links the returned instance and token ids to the follow-up tools update_agent_instance, revoke_agent_credential and revoke_provisioner_token, which tells an agent why it would call this before those. It gives no explicit exclusion (e.g. "use list_agents when you don't have a slug"), though the required slug parameter plus its "from list_agents" note covers that path.

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