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

With readOnlyHint=true already declaring the safety profile, the description still adds real operational context: the hitl_channels sub-object requires the hitl:read scope, and the tool needs a Proof account with client authentication before it can be called. That scope caveat is exactly the kind of partial-failure information annotations cannot carry. It does not cover pagination or freshness semantics, but for a snapshot read those are minor.

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 the payload enumeration, then the scope caveat, then access prerequisites as a separate block. Every sentence carries distinct information — no restatement of the tool name, no filler.

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 exists, and the description compensates by enumerating the returned fields, so an agent knows what it will get. Auth and scope prerequisites are covered. A missing note on refresh/currency of the snapshot or on error behavior when the account lacks the hitl:read scope keeps it just under complete.

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?

Only one optional parameter (environment), and schema description coverage is 100% with a full enum, so the schema already documents it. The description adds no extra semantics for the parameter — it also speaks about output contents rather than inputs. Baseline 3 is the correct score when the schema carries the full burden.

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 ('get a one-call account snapshot') followed by an enumeration of exactly what the snapshot contains (quota projection, request health, per-channel completion rates, HITL counts, API key count). The phrase 'the same data the dashboard home renders' anchors it against the many per-resource getters in the sibling list. An agent can distinguish it from get_usage, get_settings, or get_api_key_usage 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?

Gives clear context for when this tool applies (account-level snapshot rather than per-resource detail) and an explicit routing exclusion: 'start_login does NOT open this tool,' which prevents a common misfire. It also states the account prerequisite. It stops short of naming which sibling to use instead when only one metric is needed, so it is not a full 5.

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