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

Annotations already declare a safe read-only, idempotent operation, and the description adds substantial non-obvious behavior: plan-gated fields return null and are listed per item's `locked` array, `estimates` covers sales/visits/traffic, `lockedCount` hints at more results, and it explicitly forbids estimating locked data. It also discloses that this call only returns data and that a separate sightglass_show call with the resultId is required to render cards.

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 tool returns and how it differs from its sibling, then moves to filters, then to plan-gating and the show handoff — a sensible information order. It is dense but nearly every clause carries function; the plan-gating passage is slightly long-winded.

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, the description still covers the response shape (brand per angle, locked fields, lockedCount), the plan-dependency caveat, and the required follow-up call to sightglass_show. That is everything an agent needs to call it and act on the result without guessing.

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 75%, so the structured fields do most of the work, but the description adds real meaning: 'pages' in the sort enum is clarified as 'landing pages', age band is tied to the persona the angle speaks to, and the type filter is described in prose. `days` and `limit` get no prose explanation, though their schemas carry bounds.

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 and resource ('the angles in use across every tracked brand in the trailing window') and immediately differentiates from the sibling sightglass_find_angles by noting the brand is attached to each result. An agent can pick between the two without opening either schema.

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 concrete user-intent triggers — 'what pitches are brands using on this audience' and 'find an angle nobody is running' — which map cleanly to when to call it. It implies the sibling relationship but never explicitly says when to prefer sightglass_find_angles instead, so it stops just short of full alternative routing.

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