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

Annotations already declare destructiveHint=true, readOnlyHint=false, and openWorldHint=true, so the safety profile is covered. The description adds only 'immediately', implying no pending/confirmation phase, but omits whether tokens and active sessions are terminated, whether revocation is reversible or re-grantable, and what permissions the caller needs. Given a destructive, non-idempotent mutation, that leaves meaningful gaps.

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?

One short sentence with no filler, but also no front-loaded value: it duplicates the title verbatim, so the length is achieved by omission rather than efficiency. Nothing precedes the sentence to indicate scope or effect.

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 destructive, non-idempotent, open-world mutation with three parameters, no output schema, and a caller-supplied idempotency key deserves more than a single echoed sentence. It should state the effect of revocation, the retry/idempotency behavior, and the identity scope ('this person'), none of which are covered.

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 description coverage is only 33% — only idempotency_key is documented in the schema. The required connection UUID parameter and the reason field get no explanation in either place, and the description does not say whether reason is surfaced to the affected person or logged. 'One of this person's agent connections' only weakly implies that connection identifies the target.

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 verb+resource pair (revoke a connection) is identifiable, but the sentence is essentially the title repeated. It says 'one of this person's agent connections' without clarifying how that connection is identified or what 'agent connection' spans, and it never distinguishes itself from nearby siblings such as summer_account_connections_list or summer_agent_exclusions_list.

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?

No guidance on when to revoke versus when to list, exclude, or disconnect via another tool. There is no note that a connection ID must first be obtained from summer_account_connections_list, and no prerequisites or exclusions are stated. The only hint is the word 'immediately'.

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