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

Annotations already establish read-only/idempotent/non-destructive, and the description adds substantial context beyond them: nothing is rendered to the user until sightglass_show is called, the show call does not re-search, plan-gated fields come back null and are listed in `locked`, and the agent is told never to estimate locked data. These are exactly the behavioral constraints an agent needs and cannot infer from the schema.

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 is front-loaded in the first sentence and the operational constraints follow in a sensible order. It is dense and long for a single paragraph, with mild redundancy between 'Returns data only: nothing is shown to the user yet' and the later show-call instruction, but nearly every clause carries real information.

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 fully describes the return: a 0-100 position per axis, raw similarity, `isYou` marking, null/locked fields, and `lockedCount`. Combined with the parameter and follow-up guidance, an agent has everything needed to call it and interpret the result.

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 the baseline is 3; the description earns an extra point by explaining semantics the schema cannot: axes override lens, omitting `high` auto-derives the opposite, the user's own company and Brand Studio personas are always included and flagged isYou, and `companyRefs` omitted means top companies with the project's own company force-added.

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 gives a concrete verb-plus-resource ('Place personas, ads, landing pages or companies on one or two "this vs that" axes') and specifies the output shape (0-100 position per axis plus raw similarity), which is far more than the title 'Compare on a map' conveys. It does not name a near sibling such as sightglass_get_rankings or sightglass_find_personas to say how this differs, so it lands just shy of a 5.

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 explicit use cases ('where do we sit against these brands', 'which buyers are nobody's focus') and explains the axes-vs-lens choice, plus the mandatory follow-up: 'Once you know the answer, call sightglass_show once with this call's resultId'. What is missing is a when-not-to-use signal, e.g. when to prefer sightglass_get_rankings instead.

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