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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the 'never approves or executes' line largely reinforces structured data. It still earns credit by adding non-schema behavioral facts: results are scoped to this connection and only 'unexpired' items are covered, which tells the agent what will and will not appear.

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 short sentences, front-loaded with the usage trigger, followed by the safety note and exclusions. Slight redundancy between 'This read-only summary' and 'never approves or executes anything', but nothing is padded.

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, the description need not explain return shape, and with zero parameters there is no input ambiguity. The remaining essentials — scope to this connection, expiry filtering, no execution — are all stated, leaving only the missing routing to list_pending_approval_requests as a gap.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline of 4 applies. The schema is closed with additionalProperties=false and fully covered.

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 the resource precisely — unexpired pending or human-approved actions for this RetailHardHat AI connection — and the tool name supplies the 'summarize' verb. It is distinguishable from list_pending_approval_requests by implying an aggregate summary rather than an enumeration, though it does not name that sibling 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?

It opens with an explicit trigger ('Use this when checking...') and adds two prohibitions: do not use for another user's connection, and do not claim an approved action has already run. There are no named alternatives, so it falls short of full sibling routing, but the when-to-use conditions are clear.

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