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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description still adds real value beyond them: the payload is deliberately shallow (names and counts, not post bodies), and it discloses the notable failure mode that a 404 is returned not only for missing users but also for profiles that have been switched off — an important nuance an agent would otherwise misread as 'user does not exist'.

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 short sentences, front-loaded with what the resource is, then the payload scope, then the return/error behavior. No filler. Slight deduction for the slightly literary phrasing 'the shape of what they have written,' which takes a beat longer to parse than plain wording would.

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 one-parameter read with no output schema, the definition covers the essentials: what is returned, how shallow it is, and the 404 semantics. The only gap is that it doesn't state whether the handle is case-insensitive or how a private/blocked relationship affects visibility, but nothing critical to invoking it correctly is missing.

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?

There is a single required parameter with 100% schema description coverage, and the schema already tells the caller to supply the handle without the @. The description adds no format, casing, or resolution detail beyond that, so the baseline 3 applies.

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 gives a concrete resource definition — a person's public page with the tables they sit at and run plus aggregate info about what they wrote, explicitly limited to names and counts. That distinguishes it from write-side siblings like update_profile_settings, though it never names the closest read-side alternative (get_profile_settings, whoami) to sharpen the boundary.

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?

Usage is only implied: the word 'public' and 'Names and counts only' hint that this is the privacy-scoped view of another user rather than a full self-profile read, but there's no explicit when-to-use statement or exclusion pointing at get_profile_settings. The agent must infer the routing decision from the adjective 'public' alone.

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