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

Annotations already declare readOnlyHint, idempotentHint, and closed-world, so the trailing "Read-only" mostly restates structured data. What the description does add is behavioral context the annotations cannot: it is scoped to the current user's own data and reveals the shape of results (scores on a 1-5 scale, first-vs-latest comparison).

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?

One dense but front-loaded sentence covering contents, triggers, and alternatives, followed by a short safety tag. The parenthetical lists are information-bearing rather than padding, though the sentence is long enough that a reader must parse carefully to extract the routing advice.

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?

An output schema exists, so the description need not explain return formats, and the annotations cover safety semantics. Given the zero-parameter surface, the description supplies everything else an agent needs: scope, contents, triggers, and sibling routing.

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?

The tool takes no parameters, so there is nothing for the description to disambiguate beyond confirming it operates implicitly on the calling user. Baseline 4 applies for a zero-parameter schema.

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?

"Show the user's interview practice" gives a specific verb and resource, then enumerates the concrete contents (practice path, STAR answer counts, per-skill first/latest scores, newest scored answers). This is far beyond restating the name and lets an agent know exactly what payload to expect.

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 explicit trigger phrases ("how's my practice going?", "find the weakest skill") and routes two competing needs elsewhere: product cases and mock scores go to list_cases, and mock sessions go to start_mock_interview. Both when-to-use and when-not-to-use are present with named alternatives.

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