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

Annotations already carry readOnlyHint=true, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: output is scoped to the active Space, the scope can be locally overridden with space_id, and angles are business-scoped with results decided at the angle level. No behavior contradicts the annotation.

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?

Two sentences, roughly 45 words, with the action and scope front-loaded in the first sentence; the second sentence gives the override semantics. Every clause earns its place — the domain definition, the scope binding, and the alternative path are all present with zero filler.

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 zero-required-parameter, read-only list tool with 100% schema coverage, nothing needed for a correct call is missing: pagination mechanics live informatively in the cursor parameter explicitly referencing meta.nextCursor, return limits are in the schema, and scope override is in the description. The output schema is absent but unnecessary here since list endpoints of this shape have self-evident returns.

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% — all five optional parameters have type, range, pattern, and description, including defaults and max for limit and pagination for cursor. The description adds only indirect context (angle is business-scoped, which makes business_id semantically coherent) but no parameter-specific detail, so 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?

States a specific verb plus resource in the very first clause — list the angles — and immediately defines what an angle is (claims your ads argue) plus its scoping trait (business-scoped, the unit results are decided at). This clearly separates it from sibling list tools like list_ads or list_concepts, and its plural verb distinguishes it from the singular get_angle.

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?

Gives explicit operational context: the tool reads from the active Space and tells the agent exactly how to redirect — set_active_space to switch or pass space_id to override for just this one call. It does not explicitly name an alternative tool for retrieving a single angle, but the list/get verb contrast and the sibling set make that distinction natural rather than ambiguous.

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