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

Beyond the readOnlyHint/destructiveHint annotations, the description discloses polling semantics and the terminal decision values ('allow' or 'block'). It does not describe the response envelope or field names, but the essential repeat-until behavior is explicit.

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?

Two short sentences: first states the action and object, second gives the parameter source and termination condition. Every sentence carries necessary information with 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 one-parameter read-only polling tool with complete schema coverage, the description provides the call source, polling loop, and stopping condition. It is slightly light on the exact response shape or decision field, but no output schema is provided and the decision values are named.

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%, so the schema already defines approval_id as the ID from check_transfer hold decisions. The description's 'Pass approval_id from check_transfer' restates this rather than adding new 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?

The description opens with the specific action 'Poll a held pre-sign check', naming a precise resource and tying it to check_transfer. This clearly differentiates get_approval from siblings like get_status or get_pricing.

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 says to 'Pass approval_id from check_transfer' and to repeat until allow/block, which establishes the exact triggering condition and loop behavior. It does not explicitly list exclusions or alternatives, but the held-check context is enough to route the agent correctly.

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