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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered; the description instead contributes ordering semantics (starred first, then user order), a 200-point page cap, and the offset/next_offset retry loop. Return shape is sketched (spheres with point counts), just not exhaustively.

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 what the payload contains, then filtering, then pagination, then the use case. Dense but each sentence carries information; the closing 'Fits when...' phrasing is slightly loose but still functional.

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?

With no output schema and only two optional params, the description supplies enough about result structure, ordering, and pagination to call the tool correctly. Minor gaps remain around what an empty Focus section returns or what happens with an unknown sphere name.

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 coverage is 100%, so baseline is 3, but the description adds meaning on top: offset is tied to the next_offset continuation pattern and the 200-per-call limit, and sphere is framed as a filter that returns one sphere only. That is genuine semantics beyond the field 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?

Names the specific resource (the user's Focus section) and enumerates exactly what is returned: spheres with point counts and focus points with their per-sphere position. This clearly separates it from list_spheres and the mutation siblings like add_focus_point.

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?

"Fits when the user asks about their focus points" gives an explicit trigger, and "Pass sphere to see one sphere only" explains the narrowing case. No exclusion is stated against list_spheres or get_today, so routing between read siblings still requires inference.

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