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

Annotations already cover readOnly, idempotent, non-destructive and closed-world behavior, so the bar is lower; the description still adds real cost and timing context — 'counts as one request on your key' and that fresh=true is 'charged against the plan's evaluations/day budget' and evaluates now rather than reading the last scheduled evaluation. It stops short of stating auth/scoping requirements, so not 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?

The first sentence is a dense enumeration of output fields (state, previous_state, evaluated_at, effective_interval, label, enabled, channels, last_fired_at, paused_reason, agent) that an output schema already conveys, and it is front-loaded ahead of the usage guidance. Some of it earns its place — the semantics of 'unknown' with a reason and previous_state being null on first ask add interpretation — but the ordering buries the actionable routing sentence at the end.

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 two-optional-parameter read tool with an output schema, the description covers usage, parameter effect, quota cost and evaluation timing; the return-format detail is redundant rather than missing. Only the account/auth scoping of the key is left implicit.

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 100%, so the schema already documents both parameters; the description largely restates them (comma-separated UUIDs, omit for every rule) and adds only the constraint that the ids 'must all be the account's'. Baseline 3 is appropriate when the schema carries the weight.

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-resource pair ('the state of the account's Agent rules, polled') and immediately distinguishes itself from the sibling that returns saved DQL ('agent_rule_get'). An agent can route between agent_state and agent_rule_get without opening either 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?

Explicit when-to-use triggers are given (user asks about rules, alerts, signals, active conditions, when a rule last fired, plus non-English keywords) and the alternative is named with its own condition ('for the saved DQL of one rule use agent_rule_get'). The routing decision is fully specified.

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