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

Annotations already declare destructiveHint=true and non-idempotent, but the description adds the crucial nuance that this is a gated, approval-mediated flow ('Ask the user to approve', 'Returns an approval link') rather than an immediate delete — context the flags alone cannot convey. It stops short of stating approval-link lifetime, what happens if the post_id is invalid or already live, or the outcome for the requester.

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, zero filler: eligibility first, exclusion second, return value last. Every clause carries operational information.

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, no-output-schema tool the description covers purpose, eligibility, exclusion, and the return value ('Returns an approval link'), which is enough to call it correctly. The only missing piece an agent might want is how to source the post_id and whether the approval is async/pollable via get_request_status.

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 single parameter post_id is described as a UUID in the schema but has 0% description coverage, and the description never explains it — not how to obtain the ID (presumably from list_posts) nor that it must reference a post in one of the eligible states. With only one param this is a minor but real gap, landing at the baseline.

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 ('Ask the user to approve deleting') plus the resource ('post from GBPly') and enumerates the exact states that qualify (scheduled, draft, pending-review, flagged, failed). It is clearly distinguishable from sibling write tools like request_create_post, request_update_post and from the read-side list_posts.

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?

Gives both the when ('scheduled, draft, pending-review, flagged or failed post') and the explicit when-not with alternatives ('Posts already live on Google can't be deleted through the connector; remove those in GBPly or Google'). An agent knows both the qualifying filter and the escape hatch without inferring anything.

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