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

The description goes well beyond the annotations by explaining that marking queries the host without a token, that private repositories are refused, that removing the last mark of a public project immediately closes reader access, that confirmation is expected, that only specific roles may perform the action, and that both outcomes are journaled. These details materially help an agent understand the destructive side effects and authorization constraints already hinted at by destructiveHint and openWorldHint.

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?

The description is front-loaded and dense with useful operational context, covering the toggle, host check, destructive closure warning, permission requirements, and journaling. It could be slightly easier to scan if structured, but every sentence contributes to correct invocation.

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 and complete parameter schema coverage, the description supplies the critical missing context: preconditions, refusal behavior, authorization, audit logging, and the confirmation requirement for the destructive edge case. An agent has enough information 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 are already documented in the input schema, including the boolean meaning of openSource and the expected repository identifier. The description reinforces the toggle semantics but does not add parameter-level meaning beyond what the schema provides, so the baseline of 3 applies.

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?

The description states a specific verb and resource: marking or unmarking a repository already connected to a project as that project's open source repository. It also distinguishes this from connecting a repository by specifying that the repository must already be connected, so an agent can route correctly without opening the 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?

It gives clear usage context: marking checks whether the host is publicly readable and is refused for private repositories; unmarking the last open source repository of a public project immediately closes external access and should be confirmed first. It also states the required roles. It stops short of explicitly naming sibling alternatives such as set_project_public or connect_repository, but the when/when-not guidance is strong.

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