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

Annotations only declare destructiveHint=true and readOnlyHint=false; the description goes well beyond by disclosing that this merely stages a request, that the owner must open a link, review, and approve with their agent PIN, and that the PIN must never be handled in chat. This is exactly the kind of non-obvious behavioral context the agent needs.

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?

Four tight sentences, front-loaded with the action and its key precondition, then the safety-critical approval flow. Every sentence earns its place with no filler.

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, approval-gated operation with no output schema, the description covers the precondition, the exclusion, and the full staged-approval lifecycle. Nothing an agent needs to invoke it safely is missing.

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 100%, so both `name` and `workspace` are already documented in the schema, and the description adds no syntax or format detail beyond that. Baseline 3 is appropriate when the schema carries the parameter burden.

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?

Specific verb+resource (delete an access role) with the added scope constraint that the role must have no followers, which immediately distinguishes it from creation/rename siblings. An agent knows exactly what this does and what state the target must be in.

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?

States the prerequisite explicitly (move members and API keys first via assign_access_role) and the exclusion (workspace default role can't be deleted), which is strong when/when-not guidance. It names a related tool for the prerequisite step but no true alternative deletion path, so it falls just short of a full 5.

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