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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so safety and repeatability are covered. The description adds only 'latest' (freshness) and 'private' (access is gated), without describing the shape of the bundled return payload — a real gap given there is no output 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?

A single sentence with no filler; the payload contents are front-loaded and immediately scannable. It is dense with jargon, but no sentence is wasted.

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 one fully documented parameter and read-only annotations, the call mechanics are adequately covered, and the description partially compensates for the missing output schema by naming the five components returned. It stops short of explaining how those components relate or what 'plan stack' and 'memory tier summary' actually contain.

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 description coverage is 100% and the 'session' parameter is documented as a private bearer capability from check_in that must never appear in a URL. The description itself says nothing about the parameter, so it adds no meaning beyond the schema — baseline 3 applies.

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 verb 'Collect' plus an explicit enumeration of what is retrieved (consolidation report, pending status, snapshots, plan stack, memory tier summary) tells an agent this is a read that bundles several state views. The purpose is clear, though the enumerated items are domain jargon and no sibling (e.g. 'rest', 'consolidate') is named for contrast.

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?

There is no statement of when to call this versus 'rest', 'consolidate', or 'consolidate_apply', nor any prerequisite or exclusion. The 'deep_' prefix implies a heavier counterpart to 'rest', but that is inference rather than guidance.

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