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

Annotations already declare destructiveHint=true and idempotentHint=true, yet the description adds material context on top: that only the direct grant is withdrawn while role/rule access survives, the Admin permission requirement, and the human-confirmation workflow. This is exactly the additional behavioral detail the annotations cannot express.

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 sentences, each front-loaded and purposeful: scope, human-facing analogy plus permission, then the destructive-call protocol. No filler and the most important constraint lands first.

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, boolean-gated mutation with no output schema, the description covers purpose, side effects, prerequisites, and the confirmation protocol. An agent has everything needed to invoke it safely and correctly.

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 all three parameters (including project's nullable default and userId's source) are already documented. The description restates the confirm semantics rather than adding new parameter meaning, so the 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+resource ('Withdraws one member's direct grant on a project') and immediately bounds the scope: role- and rule-derived access 'stays'. This distinguishes it from grant_project_access (the inverse), remove_member, and delete_access_rule without needing the schemas.

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 the selecting condition clearly via the 'Mirrors the remove button on a grant in a project's Access tab' analogy, states the prerequisite ('needs project Admin on that project'), and spells out a two-step protocol (call without confirm, then pass confirm: true only on agreement). It stops short of naming a sibling tool as the alternative for other access-removal cases, so it is clear context rather than explicit when-not routing.

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