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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is partly covered. The description still adds real value beyond them: it specifies exactly what is destroyed (the sign-in), the immediate consequence (cannot read or change anything), and the reversibility nuance ('until it connects again'), which counters the assumption that a delete is permanent.

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: effect first, then the usage constraint, then parameter sourcing. Every sentence earns its place and nothing is redundant with the title or annotations.

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 tool with no output schema, the description covers what happens, when to call, and where to get the parameter — enough to invoke it correctly. It does not address what is returned or how failures (invalid/already-deleted client_id) surface, which would complete the picture.

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 0%, so the single required client_id would otherwise be undocumented. The description supplies its provenance ('from list_agents'), which is genuinely useful for discovery, but nothing about format, length limits, or behavior on an unknown/already-revoked client_id. That is adequate but leaves a real gap for a 0%-coverage parameter.

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 ('delete_agent' / 'Disconnect one agent') and immediately defines the scope of the effect: the sign-in is deleted and it can no longer read or change anything. This clearly distinguishes it from list_agents and from other delete_* siblings, which target different resources.

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?

'Only on the user's explicit request' gives a clear precondition for calling and effectively acts as a when-to-use guardrail for a destructive operation. It does not name an alternative (e.g., a revoke/pause action) or a when-not case beyond the explicit-request bar, so it falls short of score 5.

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