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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=true, so the safety profile is partly covered. The description adds genuinely new behavioral scope: revocation is immediate, and it does NOT disconnect accounts already linked — which is exactly the blast-radius question an agent needs answered for a destructive call. It stops short of describing failure modes or permission requirements.

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, each doing distinct work: effect/scope, when to use, and how to source plus confirm the id. The most decision-critical fact (immediate stop, existing connections unaffected) is front-loaded.

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 destructive mutation with no output schema, the description covers what gets destroyed, at what granularity, the sourcing of the required id, and the human-confirmation gate. The only shortfall is the undocumented workspaceId and no mention of what a successful or failed revoke looks like, though annotations carry part of that load.

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 67%: linkId's origin and idempotencyKey's retry semantics are already documented in the schema, and the description only echoes the list_connect_links sourcing. workspaceId has no description in either the schema or the description, so the parameter story has a real gap. Baseline 3 is appropriate.

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 and resource ('Revoke a client connect link') and immediately scopes the effect: the link stops working at once while already-connected accounts persist. That distinguishes it clearly from siblings like list_connect_links and get_connect_url without the agent needing to open any schema.

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 explicit triggering conditions ('link was sent to the wrong person or is no longer needed'), tells the agent where the required id comes from (list_connect_links), and adds a hard prerequisite to confirm with the human first. Nothing about when to invoke is left to inference.

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