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

Annotations already declare destructiveHint=true, idempotentHint=false, openWorldHint=true, so the safety profile is known. The description earns credit by explaining what 'destructive' actually means here (a toggle, not a data change) and by disclosing the optimistic-concurrency failure mode: stale revisions fail rather than overwriting newer selections.

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 with no filler, and the non-effect ('does not disconnect Linear') is placed early where it matters. The garbled 'connected team with BOTH current revisions' phrasing costs it some clarity per unit of length.

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?

An output schema exists and annotations cover the risk profile, so the description needn't explain returns. However, for a resource-selection tool it never says what is being selected (teams? projects? issues?) or what happens to resources left unselected, which is the central ambiguity an agent would need resolved.

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 100% and the nested object's own description already says the revisions come from provider_resources_read, so the description largely restates structured data. The failure semantics for the expected_*_revision fields is a small addition, but 'enabled' and 'agent_id' are left entirely to the 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?

States a specific verb pair (enables/revokes) and resource (Agent access to a connected Linear team), which distinguishes it from provider_disconnect and provider_resources_read. The phrase 'connected team with BOTH current revisions' is awkwardly worded and blurs whether the selected resource is a team, a project, or a set of issues.

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?

Explicitly scopes out the neighboring operations ('does not disconnect Linear or change existing issues'), routing disconnection to provider_disconnect. It also points at the prerequisite flow by noting revisions come from provider_resources_read, though it never states the preconditions (must be connected, must have read revisions first) in a directive way.

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