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

Annotations cover the safety profile (readOnly=false, destructive=false, openWorld=true), and the description adds real value on top: the retry-safe behavior tied to idempotency_key and the mode-dependent refresh semantics. It does not describe the returned artifact, but it meaningfully supplements the annotations rather than repeating them.

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?

Three tight sentences, each earning its place: purpose and modes first, the revoke alternative second, retry semantics last. No filler or redundancy.

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 an 11-parameter, nested-object, no-output-schema tool, the description covers purpose, mode selection, revocation path, and idempotency. It omits what the call returns (presumably the link URL), which would help since no output schema exists.

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 82%, so the schema already documents nearly every parameter (mode, cadence, password, expires_at, workspace_id). The description echoes the mode/cadence relationship without adding format or syntax detail beyond what the schema provides; baseline 3 is appropriate.

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 ('Create') and resource ('shareable link to a workspace report') and clarifies the two modes (snapshot vs live). It distinguishes itself from link-creating siblings (create_short_link, create_client_review_link) by resource scope, though it never names them 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 clear usage context: the snapshot-vs-live choice is explained, and it names aidelly_revoke_report_link as the tool that disables the link. It does not, however, tell the agent when to prefer this over the other link-creation siblings.

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