pup_healthcheck

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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses a genuinely useful behavioral trait: a structured error.kind taxonomy (no_credential, credential_rejected, verification_pending, edge_blocked, timeout, transport, http) that distinguishes credential failures from infrastructure failures before PickUp Patrol ever judged the credentials. It also confirms the tool is read-only and never returns the credentials, which is exactly the kind of consequence disclosure annotations cannot carry.

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?

It is a single dense sentence-plus-em-dash-list, but the purpose and outputs are front-loaded before the error taxonomy, and every clause carries information an agent needs (what it verifies, what it reports, how failures are classified). Nothing is padding.

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?

With no input parameters, no output schema, and only two annotations, the description must carry the return-value burden itself — and it does, enumerating the server version, the students visible to the account, and the error.kind values on failure. An agent knows both the preconditions and the shape of the result.

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?

This tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. The description correctly adds no parameter discussion, only outcome semantics.

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 states a precise verb and object — verify that configured credentials sign in and the PickUp Patrol API answers — and names the concrete outputs (server version, visible students). Every sibling tool fetches domain data; this one is unambiguously the connectivity/auth probe, so an agent can route to it without opening any 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?

The context of use is clear (diagnosing whether the account can reach and authenticate against the API), and the failure taxonomy implicitly tells the agent this is the tool to reach for when another call fails. However, it never explicitly says 'call this first' or 'use this when X tool returns an error', nor does it exclude any scenario, so it stops short of full when/when-not guidance.

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