Outline, map or zoom view

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

Goes well beyond the readOnly/idempotent annotations: 12KB truncation with a `truncated` flag, id renewal on zoom with the global baseline left untouched, and the concrete return shape of map (entries, offset, returned, total, nextOffset, observationId). The note that zoom 'renews ids' is a meaningful side effect an agent must know before reusing ids.

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 the three modes and then the escalation rule, with no filler sentences. It is densely parenthetical, which slightly hurts scannability, but every clause carries 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?

No output schema exists, so the description compensates by describing the structuredContent for outline and the field set for map, plus the href/embedded-resource convention inherited from browser_open. Combined with the per-view requirements and optional sessionId, an agent has everything needed to call this correctly.

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 schema already documents id, view, offset, and sessionId. The description still adds interpretation—zoom 'observes ONLY that subtree' and map offset means 'pages actionables beyond the top'—which clarifies intent rather than merely restating the schema.

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 resource (expanded views) and enumerates the three modes—outline, map, zoom—with the distinguishing trait of each (full structure trimmed to 12KB, paginated actionables, single-subtree observation). It contrasts against 'the digest' and references browser_open, but never names the digest-producing sibling tool outright, so sibling differentiation is implied rather than explicit.

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 a clear escalation rule ('Explicit escalation — digest first') and conditions per mode: map/offset for pages beyond the top, zoom/id for a region or card detail. There is no explicit when-not guidance beyond the digest-first ordering, and the alternative tool is referenced by the colloquial term 'digest' rather than by name.

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