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

Annotations only flag destructiveHint=true and idempotentHint=false generically; the description converts that into concrete consequences: socials, theme, links, and projects replace what is stored, while other omitted fields stay, and passing link ids preserves click history. That is precisely the information an agent needs to avoid silent data loss, and it goes well beyond what the annotations convey.

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?

Content is densely front-loaded: purpose first, then prerequisite, then setup fields, then update semantics, then the handle caveat. The opening clause is a long laundry list of profile sections, but virtually every sentence carries actionable information and nothing is 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?

For an 11-parameter, nested, destructive, no-output-schema tool, the description covers the workflow, the destructive replace behavior, and the risky handle-change path. Minor gaps remain around concurrency (expectedVersion) and the setup-only nature of searchIndexing, both of which the schema documents, so the description is adequate without being fully self-contained.

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 73%, and the description adds real meaning: name is required in practice for setup, the handle is free on every plan, pins are capped at 2, projects are the user's own sites, and link ids preserve click history. It leaves expectedVersion and searchIndexing to the schema, which documents them, so this is close to complete but not exhaustive.

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 uses a specific verb+resource ("Set up or change the user's ATTIM profile") and then enumerates exactly what the profile comprises: one public link-in-bio page at <handle>.attim.link with name, bio, avatar, social icons, pinned links, other links, and Projects. This clearly distinguishes it from siblings like get_public_profile, which it explicitly names as a prerequisite read.

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?

It gives an explicit prerequisite ("Call get_public_profile first"), an explicit setup workflow (ask for name, short bio, optional https avatar URL, links, desired handle), and explicit when-changing semantics ("omitted fields stay"). It also flags the consequential exception — handle changes are rate-limited (Free: once a week) with a 30-day redirect — so an agent knows when to warn the user.

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