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

With no annotations, the description carries the full burden and does so well: it discloses the return payload (URL, route list, ownerToken), the seven-day lifetime without an account, the six-hour re-read for URL sources, and format-specific data handling (HAR headers/cookies dropped, db.json records served as-is, generated data coherent and generated once). Gaps remain around failure modes for invalid documents, auth requirements, and rate limits, which keeps it below a 5.

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 core action is front-loaded, which is good, but the format enumeration is a single sprawling sentence with deeply nested parentheses that is hard to parse and could be compressed or bulleted. The trailing sentences about return value, data generation and lifetime are tight and earn their place, partially offsetting the bloat.

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 six-parameter tool with no output schema, the description compensates well by describing the return value, the mock lifetime, and the refresh behavior of URL-sourced mocks. The notable omission is that all six parameters are optional and the description never states that at least one of `spec` or `url` must be supplied, nor what happens when neither is given.

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 description coverage is 100%, so every parameter is already documented in the schema, and the description largely restates those semantics (spec vs url, auto re-read, slug being Pro-only, locale). The one addition of value is the six-hour refresh cadence tied to `url`, but that is behavioral rather than parameter-level meaning, so the baseline of 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?

Opens with a specific verb and resource ('Create a hosted mock') and immediately enumerates the accepted source formats, so the agent knows exactly what the tool produces. It is unmistakably distinct from siblings like get_mock, list_mocks, regenerate_mock or sync_mock, which operate on already-existing mocks.

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 implied by the creation verb and by the explicit spec-vs-url fork ('Give the document in `spec`, or its public address in `url`'), which is genuine routing guidance. However, no sibling is named as an alternative and no exclusion is stated (e.g., when to use regenerate_mock or sync_mock instead of creating a new mock), so the agent must infer that this is the entry point.

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