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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description adds substantial context: the effect is a real, irreversible push ('收不回'), processing is serial, partial failures must be diagnosed individually, and it documents two error paths (organization_application_resolved for conflicting prior review, organization_rate_limited with retry-after).

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-loads the auth/role gate and the 100-item cap, then uses an arrow flow for the sequence and terse clauses for edge cases. Dense but every clause carries operational meaning; no filler.

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 does the heavy lifting by describing success/failure reporting and specific error codes. It stops short of describing the exact return payload shape, but covers enough for correct invocation.

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 still adds meaning by explaining that preview defaults to true and that execution requires an explicit preview=false, plus how the decision reasons should be surfaced to the user.

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 verb+resource (bulk-review organization membership applications) with scope and role gating (OWNER/ADMIN, max 100). It distinguishes itself from the sibling list_organization_applications by naming that tool as the read-side counterpart it feeds from.

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 an explicit end-to-end workflow: list_organization_applications(pendingOnly=true) → preview → confirm → execute → report. It clearly states preview=true first to read names/reasons verbatim, then preview=false to actually act, leaving no ambiguity about when each mode is used.

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