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

Annotations supply only destructiveHint=false, so the description carries the behavioral burden and does so well: it declares no persistence, no publishing, no contacting, blank-out behavior for unclear fields, source-text attribution, and an explicit prompt-injection defense (instructions inside the material are not executable). It also explains the re-preview semantics without a model re-run, which is non-obvious operational behavior. Nothing here contradicts destructiveHint=false.

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 prerequisite tag is front-loaded ahead of the purpose, which is the right ordering for an agent scanning for eligibility. The body is a single semicolon-chained sentence — dense but each clause carries distinct information (scope, evidence, exclusions, injection defense, preview loop). Slightly hard to parse in one pass.

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 unannotated parameter and no output schema, the description must cover auth, side-effect profile, and the shape of the result, and it largely does ('show candidates first' tells the agent a preview-like payload comes back). It does not describe what fields the candidates contain, which would matter for the downstream edit step it references.

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?

The schema provides zero description coverage for the single 'text' parameter, so the description must compensate, and it does: it specifies the accepted content as pasted business-card/introduction/supply-demand text. It does not mention the 16,000-character limit or the single-string shape, but the content type is the material question an agent needs answered.

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 pairs a specific verb (整理/parse-and-organize) with a specific resource (pasted business-card, introduction, supply/demand text) and adds scope detail (preserve source evidence, separate supply from demand). An agent can tell this is a text-normalization step rather than a save or commit action. It stops short of naming its near-identical siblings, so differentiation is inferential rather than stated.

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?

Prerequisites are stated up front (login + existing AI authorization) and the workflow is sketched (show candidates first; after editing, re-preview without re-running the model). However, the sibling set contains preview_network_contact_intake and commit_network_contact_intake, and the description never says how this tool relates to or differs from them. For an agent forced to choose among three similarly-named intake tools, that selection rule is left to inference.

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