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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description's genuinely additive items are the authorization rule ('members are refused') and the result cap ('up to 5 recent documents'), but it omits what happens when the named collection does not exist or is not shared.

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?

The first sentence is dense, nesting the manager role constraint ahead of the actual action and packing a long parenthetical definition mid-sentence. All content earns its place, but front-loading the verb and resource would help the agent parse faster.

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 appropriately carries the return-value burden by listing count, rules, apps, and recent documents, plus the read-only and role constraints. Only the not-found / non-shared edge case is left uncovered.

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 single parameter is self-documenting ('Omit for all of them'), so the baseline is 3. The description adds no syntax, matching, or case-sensitivity detail for the collection name beyond what the schema states.

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 concrete verb and resource ('see the organization's shared collections') and enumerates the returned payload: count, rules, consuming apps, and up to 5 recent documents. The parenthetical defining 'shared' via the crow.db declaration makes the concept unambiguous against siblings like tool_data or org_apps, though no sibling is named explicitly.

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 usage trigger: 'Check this, or ask, before creating a collection another app may already have', which tells the agent to consult this before a write elsewhere. It also scopes the audience ('as an organization's manager'), but names no alternative tool for the case where the caller is not a manager.

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