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

Beyond stating that it is read-only and idempotent, the description adds critical behavioral traits: it explicitly states that the tool 'Does not move your unread cursor,' which is a vital piece of information for managing the user's reading progress.

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 highly dense but impeccably efficient. Every sentence contributes critical information regarding scope, constraints, or workflow without unnecessary fluff.

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?

Given the complex, multi-stage nature of the retrieval (T0, T1, T2) and the required operational sequence, the description provides a complete picture for the agent without requiring external lookups.

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 schema coverage is 100%, the description adds vital semantic meaning by explaining that an omitted campaign_id uses a default deck, and describes the practical function of max_tokens regarding the extent of campaign activity included.

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 defines the purpose as getting oriented or reading history. It specifies the scope by breaking down the retrieved data into three distinct parts (T0, T1, T2) and differentiates itself from other tools by referencing 'space_state' for open work.

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 instructions on when to use it ('on return after a gap or to read history') and a clear alternative for specific use cases ('For open work... use space_state'). Furthermore, it defines the necessary post-call workflow (call fast_forward afterwards).

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