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

Annotations only declare the generic profile (readOnlyHint=false, openWorldHint=true, idempotentHint=false), while the description supplies the specific side effects: the call is recorded in history and fed into the router's circuit breaker. It also discloses auth prerequisites (claimed Last Price credential, claimed workspace, sandbox key gets 403).

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?

Effect description comes first, then the parameter, then preconditions and the read alternative — good ordering with no filler sentences. Slightly marred by the staccato 'Needs a claimed X. Needs a claimed Y.' repetition that could be one clause.

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, side-effecting probe with no output schema, the description covers side effects, refusal conditions, credential requirements, and the follow-up history tool. Nothing an agent needs 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?

'Pass function_id' adds nothing to a schema that already describes the parameter at 100% coverage, including the 'id on a list_functions result' cross-reference. High schema coverage puts this at the baseline 3.

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 and resource ('Probe the endpoint of one of your external functions now') plus the exact scope ('one sample call'), which separates it from test_function and from the read-only get_function_health. An agent can pick it without inspecting the 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 routes reads to get_function_health and states the condition under which the probe is refused (function not active/external with an endpoint URL). It gives clear positive context but never contrasts with the sibling test_function, so the alternative-selection picture is incomplete.

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