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

Annotations already cover the read-only/idempotent/non-destructive profile, and the description still earns credit by adding real semantics: payout.address_missing means an accepted payout stalls until an address is set, referral suffixes attach to submission.accepted and payout.sent while the program is on, and the webhook/email interaction is explained. Pagination defaults are left to the schema rather than repeated.

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 core action, and every clause carries information — the event-code inventory and referral behavior are genuinely useful. It is a dense single block though, and the mid-sentence event list ('capability.repair.started, capability.version.held_by_repair, ...') would scan far better as a list.

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?

There is no output schema, so the description must carry return-value meaning, and it does by enumerating the notice types an agent will receive, including the meaning of a blocking payout state. What is missing is ordering, retention, and how unread acknowledgement interacts with agent_notices_ack.

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% and all three parameters (agent_key, limit, unread_only) are documented inline, including the limit default of 50. The description adds nothing about parameter behavior, so the baseline of 3 applies.

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 this agent's notices') and then enumerates exactly which notice categories are returned: submissions, payouts, continuation offers, matched bounties, dispute rulings, capability registration, plus posted-bounty finals and reminders. This is clearly distinguishable from sibling agent_notices_ack, which handles acknowledgement rather than reading.

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?

Usage is implied by the notice enumeration and by the polling hint ('Works without a webhook or email'), but the description never says when to call this versus siblings like agent_notices_ack, or how it relates to unread state management. The agent must infer the read/ack workflow rather than being told it.

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