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

Annotations declare destructive=true, idempotent=true and openWorld=true, and the description goes well beyond that: it discloses the pre-save trial run for probe-affecting changes, that a failing trial leaves the existing test unchanged and returns an error naming the failure, that metadata-only edits skip the run, what is returned, and that private/loopback/cloud-internal targets are refused. This is exactly the mutation-behavior context an agent needs and cannot infer from the hints.

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?

Front-loads the critical overwrite warning in the first sentence and every following sentence carries distinct information (destinations scope, trial-run trigger, error semantics, return value, URL restriction). It runs long as a single dense paragraph, so it is slightly heavier than needed, but there is no 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 a 28-parameter destructive mutation with no output schema, the description covers the overwrite contract, the validation side effects, failure and error behavior, the returned value, and a hard constraint on target URLs. Nothing an agent needs in order to call 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?

Schema description coverage is 100% across all 28 parameters, so the schema already carries the per-field meaning, enums and variables; the description only groups fields into 'target, credential, assertions or timeout' and defers the rest to create_api_test. Per the baseline rule, 3 is correct when the schema does the heavy lifting, and the description adds only a pointer rather than new field-level meaning.

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 ('Replace the entire configuration') plus resource ('an existing API test') and immediately clarifies the overwrite semantics versus a patch. It explicitly names the sibling it is not (set_api_test_destinations) and points to create_api_test for the field set, so an agent can distinguish it from neighbors without opening a schema.

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?

Explicitly tells the caller to pass every field they want to keep, routes notification changes to set_api_test_destinations, and ties parameter shape to create_api_test. It also gives the use-case split between probe-affecting fields (trial run) and metadata-only fields (no trial run), which is exactly the decision an agent must make before calling.

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