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

Annotations already flag destructive and non-readOnly behavior; the description adds that remove true revokes access and changes require 'change anything' permission, plus default permission push. It does not discuss idempotency or rate limits, but adds useful mutation context beyond annotations.

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?

Compact and front-loaded with the no-username listing case, then mutation cases. The dense semicolon structure is efficient but slightly telegraphic.

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 multi-mode destructive tool with no output schema, the description covers modes, permission values, default, and required scope. It omits return details or pending-invitation specifics, but is sufficient for correct invocation.

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 only 25% (only repo is described), so the description carries username/remove/permission semantics: optional username switches list vs mutate, remove true revokes access, and permission enum values with default push are supplied. This compensates strongly for undocumented schema fields.

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 specific verbs and resource: list collaborators and pending invitations, invite, change permission, and remove. The conditional 'without username/with username' distinguishes its modes; it lacks explicit contrast with sibling tools like gh_repo_settings, but the collaborator resource is clear.

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 maps parameter states to behavior: omit username to list, provide username to invite/change, remove true to revoke access. Covers when to use each branch but gives no when-not guidance or alternative sibling routing.

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