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

Annotations already carry readOnlyHint/idempotentHint/destructiveHint, and the description adds behavior beyond them: the four possible return states, the approval workflow continuation, and the purchase-specific assurance 'Reads only; spends nothing' — meaningfull context for a tool in a purchase flow. The description aligns with annotations; no contradiction.

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?

Six sentences, each carrying distinct load: purpose, pre-condition, approved path, denied path, polling cadence, and safety. Front-loaded with the core scoping sentence, and the 'spends nothing' closing reinforces the safety profile without bloating.

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 an output schema present (return values need not be spelled out) and annotations covering the safety profile, the description still adds return states, reason/deadline, and the conditional next steps an agent must take. For a one-parameter read tool, nothing needed 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 coverage is 100% — the single approval_id param is already described as returned by apiosk_execute. The description adds a workflow constraint beyond the schema: the same approval_id must be reused when re-calling apiosk_execute after approval. That is genuine added semantics, though the schema does the heavy lifting.

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 opens with a specific verb+resource pair — 'Read the state of a purchase' — and enumerates the possible outcomes (pending, approved, denied, expired) plus what is returned (reason, deadline). This distinguishes it cleanly from siblings: it is the read-only status check, vs apiosk_execute which triggers and executes purchases.

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?

It gives an explicit trigger precondition naming the sibling tool ('Call it only after apiosk_execute returned status: approval_required'), and prescribes follow-up behavior for each outcome: re-call apiosk_execute on approval, do not retry on denial, ask the user instead. It even caps polling cadence ('at most once every few seconds'), leaving no ambiguity about when to use it.

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