cpu_get_changes

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

With no annotations provided, the description fully carries the behavioral transparency burden. It discloses key stateful behavior: the reply carries a new version for subsequent calls, the server.reachable flag indicates API availability, and it explains the implications of false (actions will fail) and the reconnection policy. This goes well beyond the bare minimum.

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?

Though relatively long, every sentence earns its place: it opens with the purpose, then explains the parameter usage, and then covers the important server.reachable edge case. The structure is logical and front-loaded, with no redundant fluff or repetition.

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?

The description is sufficiently complete for the tool's complexity. It explains the versioning mechanism, the meaning of the server.reachable flag, and the recommended polling behavior, even covering the post-outage recovery step. While there is no output schema, the description highlights the critical return fields and their roles, making the tool easy to invoke and interpret.

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?

The schema already fully documents the single parameter sinceVersion, including its type, default, and meaning ('Omit or 0 to return every cell'). The description adds no new semantic information beyond what the schema provides—it simply restates the same concept in prose. Therefore the baseline of 3 is appropriate.

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 explicitly states the tool's function: 'Get only the cells that changed since a given version'—a specific verb with a clear resource and scope. It also distinguishes itself from related tools by framing it as a way to 'react to other players without re-reading the whole map', clearly differentiating from full-map retrieval tools like cpu_get_map.

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?

The description provides explicit usage context: use it to avoid re-reading the whole map, pass the version from a previous response, and omit sinceVersion for a full snapshot. It also gives direct guidance for the unreachable case ('keep polling cpu_get_changes rather than retrying actions') and after an outage ('call once with sinceVersion 0 for the full picture'), effectively steering the agent away from alternatives.

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