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

Annotations already declare read-only, idempotent, and non-destructive hints. The description adds critical behavioral context: the caller must manage the marker themselves, and pagination uses next_since/has_more. This goes beyond what annotations provide and helps the agent understand statefulness and response structure.

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 description is dense but each sentence carries essential information. It front-loads the main action, then explains prerequisites, pagination, and fallback help. No redundant phrasing, and it remains compact given the complexity of the API.

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 read-only feed tool with no output schema, the description is remarkably complete. It covers both usage modes, pagination, state management, and even provides fallback help via front_door and a URL. An agent has all necessary context to call and handle the tool correctly.

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?

While the schema documents that 'kind' and 'limit' require 'since', the description explains the overall logic: omitting all three yields a marker, and 'change_id is the only per-notice cursor'. It clarifies the inter-parameter relationships and the meaning of 'since' as a marker, adding value beyond the schema's descriptions.

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?

The description clearly states the tool's two modes: obtaining a marker and reading later changes, using specific verbs like 'Get' and 'read'. It differentiates itself from sibling tools by focusing on the public change feed, and explicitly names the per-notice cursor 'change_id', making its purpose unambiguous.

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?

It provides explicit usage rules: 'Kind and limit require since; omit all three to obtain a marker.' It also describes the pagination workflow ('Follow next_since until has_more is false') and the need to keep the marker because 'the city stores no durable reader history'. This gives clear when-to-use and how-to-use guidance.

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