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

Annotations already declare destructive/idempotent/openWorld, yet the description adds substantial context beyond them: the link stops resolving immediately, past analytics are preserved in document totals, the shareId becomes unaddressable, the default-link validation error, the confirmation preview showing link and traffic, and the untrusted-content warning for author/viewer text. This is exactly the extra disclosure the destructive hint cannot carry.

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 destructive action and its immediate effect are front-loaded in the first sentence, and the remaining clauses each carry distinct information (analytics retention, restore path, default-link exception, confirmation, trust warning). The later sentences are dense and slightly run-on, but nothing is redundant.

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?

For a 5-parameter destructive tool with no output schema, the definition covers effect, post-deletion state, retention of analytics, reversibility, the only hard failure case, and the human-confirmation interlock. An agent has everything needed to call it correctly and warn the user appropriately.

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 baseline is 3, but the description adds real meaning: it explains that analytics remain readable by docId after deletion, and it describes the confirm-before-acting flow that gives purpose to the confirm/confirmationToken/alwaysAllow parameters (which the schema only names). linkId's provenance is left to the schema description.

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?

Opens with a specific verb+resource: 'Delete one share link.' It then immediately bounds the scope ('one share link', 'a document's default link cannot be deleted'), which lets an agent distinguish it from lnkdrp_delete_doc, lnkdrp_delete_project_link, and lnkdrp_restore_share_link without opening any schema.

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?

Provides an explicit when-not case ('A document's default link cannot be deleted (validation error); it can be disabled') and names the inverse operation (lnkdrp_restore_share_link), so the agent knows both the exclusion and the recovery path. It lacks an explicit positive 'use this when...' statement, but the effect description plus the named alternative covers the routing decision well.

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