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

With no annotations, the description carries the full burden and does disclose meaningful behavior beyond the schema: repos is the canonical enabled set minus disabled repos and is sorted, installed is false in the no-installation case, and install_url degrades to the Settings page when the App is unconfigured. Auth requirements and whether the list spans multiple installations are not covered, keeping it from a 5.

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?

Purpose is front-loaded in the first sentence, then edge cases, then the memory-overlay disambiguation. The final sentence is dense and slightly convoluted in phrasing, but each part carries information an agent would otherwise get wrong.

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 zero-param, no-annotation tool with an output schema, the description supplies what the schema cannot: connection-state semantics, disabled/ordering behavior, and the trap of confusing it with memory session binding. Only the auth/scope question (one installation vs all) is left unaddressed.

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?

The tool takes zero parameters, which sets the baseline at 4. The description correctly spends none of its length on input semantics and instead handles the return-side disambiguation.

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 opening line names a specific resource — the repos served by this org's GitHub App installations — and adds that it doubles as the GitHub-connection check, which distinguishes it from github_repo_get and github_code_search. It is a noun phrase rather than a verb+resource (implicitly "list"), and it never names the sibling it is closest to, so it stops short of a 5.

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?

"This is whether GitHub is connected" implies the primary use case (connectivity probe) without stating it as guidance, and the closing sentence gives one explicit when-not: don't use this to read a memory tool's bound/session_bound overlay. There is no stated alternative for fetching a single repo or for listing repos outside the org's installations.

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