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

Goes far beyond the annotations: one-use link, 60-minute expiry, scoped to the connection's account and workspace, revoked with the key or sign-in, carries no password or personal details in the URL, validation refusal of title/projectId/projectSlug/allowDownload/password when docId is set, 'forbidden' with details.code publisher_required, and a 10-link-per-person rate limit. It also flags untrusted author/viewer text in results.

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 purpose and constraints, and nearly every clause adds a distinct fact (expiry, scope, refusal rules, return shape, rate limit). It is a dense wall of text with some repetition of the docId/new-version condition, which keeps it from a top score.

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, yet the description enumerates the return object ({ uploadLinkId, url, expiresAt, mode, ... }) and ties uploadLinkId to lnkdrp_check_upload_link, the natural follow-up. Combined with the failure modes and rate limit, an agent has everything needed to call it and handle the outcome.

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 carries the field-level detail; the description adds the cross-parameter rule that matters most — with docId the five new-document fields are refused by validation, and password is stored and never returned (only passwordSet). It does not elaborate on idempotencyKey's 10-minute replay beyond what the schema already says.

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 and resource ('Creates a one-time page on the LinkDrop site where the signed-in person adds a PDF') and immediately clarifies the scope difference from a direct upload: the agent has no network/file access, the person supplies the PDF through their browser. That framing alone separates it from lnkdrp_create_upload and lnkdrp_stage_pdf.

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 strong when-to-use context ('works in every client, with no network access from the agent's environment; needs the person to open the link') and names one alternative for the publisher failure path (lnkdrp_stage_pdf adds a draft instead). It never explicitly names lnkdrp_create_upload as the contrasting direct-upload path, so the sibling routing is implied rather than stated.

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