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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds real behavioral context beyond that: the call can remain open (long-poll) until a pending request is decided or expires, which is exactly the kind of blocking semantics an agent needs and which no annotation conveys.

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 sentences, front-loaded with the resource scope, then the operational rule. No filler, and the warning about polling is placed before the parameter it points to. Slightly terse given the missing pagination note, but nothing is wasted.

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?

A zero-required-parameter read tool with no output schema, so the description need not document return values; 'including human decisions' gives a useful hint about content. The one real gap is that result_offset and result ordering are left entirely to the schema, which does not describe them either.

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 0%, so the description must carry parameter meaning. It does this well for wait — units, range 0-120, an example value, and the blocking semantics — but result_offset is completely unmentioned, leaving pagination behavior unexplained. Partial compensation for a two-parameter schema.

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 specific verb+resource combination: it reads this connector's permission and binding requests, and clarifies that the output includes human decisions. This implicitly separates it from the write-side siblings request_access and request_binding, though it never names them explicitly.

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?

There is explicit anti-pattern guidance ('Do not poll in a loop') plus an instruction to use the wait parameter instead, which is genuinely useful invocation guidance. However, it says nothing about when to choose this over request_access or request_binding, or what precondition (an existing request) makes it relevant.

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