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

Beyond the read-only/idempotent annotations, the description discloses several non-obvious behaviors: results are empty until sufficient ads/pages are read, plan-gated fields return null and are named in each item's `locked` list, `lockedCount` signals hidden results, and the agent must tell the user the data is on a higher plan rather than estimating. It also states the call is data-only and renders nothing until sightglass_show is called.

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?

Purpose and return shape are front-loaded, and the plan-gating and show-workflow sentences carry real operational weight. The prose is dense and runs together several distinct ideas in long sentences, but almost nothing is redundant.

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?

There is no output schema, so the description takes on the burden of describing the return shape — which it does field by field — plus empty-state behavior, plan gating with `locked`/`lockedCount`, and the required follow-up call to sightglass_show. Everything an agent needs to call and then correctly present results is present.

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% with three well-annotated parameters, so the baseline is 3. The description adds plan-context meaning (the workspace's plan governs what fields are locked) but says nothing specific about companyRef, projectId, or workspaceId beyond what the schema already documents.

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 defines the resource concretely — a brand's customer personas plus the exact fields each contains (segment nickname, buyer situation, ad share, angles, offers) — so an agent can tell it apart from siblings like sightglass_find_angles or sightglass_find_offers. It stops short of explicitly naming an alternative tool, but the scope is unmistakable.

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 gives concrete when-to-use framing: "Use it to answer 'who is this brand selling to' or to compare two brands' audiences," and states the precondition that results are empty until enough ads and pages exist. It also sequences the workflow (call sightglass_show once with resultId). No explicit exclusions or named alternatives, which keeps it below a 5.

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