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

Annotations already declare this a safe read (readOnlyHint=true, destructiveHint=false), and the description adds genuinely new behavior: it is a polling tool, decisions may be non-final, and the timeout semantics differ by gate type. It does not say whether polling should be backed off/rate-limited, and the return shape is only hinted at, so it stops short of full disclosure.

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?

Front-loaded with the core action in the first four words, and every subsequent clause carries operational information rather than filler. The telegraphic phrasing ('Action Gate timeout is stop') is dense but slightly ambiguous, costing a little readability.

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 one parameter, no output schema, and no annotations gap, the description covers the invocation side well. However, because no output schema exists, it should enumerate what the poll actually returns (the go/stop/wait decision shape and any pending state) instead of leaving it to inference from scattered phrases.

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% and the schema already explains approval_id, but the description meaningfully widens the source of that ID beyond the schema's 'returned when check_transfer decision is hold' to also include check_action and Write Gate tools. That is real added semantics rather than restatement.

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 ('Poll a held check') and immediately names the producing tools (check_transfer, check_action, Write Gate tools), which distinguishes it from those siblings. An agent can tell this is the read-side companion to the check/hold tools 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?

Explicit about the loop ('Repeat until the decision is final'), the failure mode for each gate type ('Action Gate timeout is stop'), the required follow-up for Write Gate ('call slack.post or crm.write again with that approval_id after the decision is go'), and an exclusion ('Email isn't supported yet'). This is close to a complete operating procedure for the tool.

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