Auth: OAuth token status (no secrets)

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

Annotations already declare readOnlyHint=true, so description not needed for that. But it adds context beyond annotations: token never returned, and that probe may trigger a refresh side effect. This is valuable behavioral disclosure. Could mention idempotency or rate limits, but sufficient.

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?

Three sentences, each with a distinct purpose: what it reports, what it never returns (and alternative), and probe behavior. No fluff, front-loaded with key info.

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?

Given it's a simple status check with one optional parameter and an output schema (presumably documenting return fields), the description covers all necessary context: function, safety, parameter behavior, and alternatives. Complete for its complexity.

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 covers the parameter with description, and the description adds context about refresh behavior. Schema coverage is 100%, so baseline 3; description adds extra nuance, earning a 4.

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 clearly states it reports token metadata (present/absent, expiresInSec, last refresh error) and explicitly says what it does NOT do (never returns the token). It also distinguishes from the auth_* tools, which do return the token. The verb 'reports' and resource 'token metadata' are specific and immediate.

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?

Provides explicit guidance on when to use (check token status) and when not (need actual token, use auth_* tools). Explains the probe parameter's effect: default no refresh, probe=true may trigger refresh. Clearly references alternatives under AVITO_MCP_EXPOSE_AUTH_TOOLS=1.

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