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

Annotations already declare destructiveHint=true and idempotentHint=false, so the description's remaining job is to add specifics. It does add one valuable fact the annotations cannot convey: cached archives are deleted alongside the access revocation. However, it never says the action is irreversible, what happens to existing sources/sync jobs, or that reconnection requires going through connection_start again.

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?

A single front-loaded sentence with no filler, and the destructive side effect is placed where it will be read. It is arguably too terse for a destructive teardown, but no sentence wastes space.

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 an irreversible, open-world, destructive operation with a required concurrency token and no output schema, the description omits critical context: reversibility, effect on downstream sources/sync, retry semantics despite an idempotency_key, and what expected_version must contain. The agent cannot safely invoke this from the description alone.

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 25% (just idempotency_key), and the description does not compensate at all. The required expected_version parameter is a concurrency/optimistic-locking token whose meaning is undocumented anywhere, and the description only vaguely gestures at company/environment via 'this company/environment' without tying them to the parameters.

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 (disconnect) plus the resource (GitHub source access for a company/environment) and names the concrete side effect of removing cached archives. It is clearly a teardown operation, distinguishable from connection_start or connection_read, though it never explicitly contrasts itself with siblings such as sources_save or account_connections_revoke.

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 no statement of when to use this versus alternatives (e.g. sources_save to reconfigure, sources_sync to refresh, account_connections_revoke), and no preconditions such as required permissions or whether the GitHub connection must exist first. The agent must infer usage entirely from the name.

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