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

Annotations already cover readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds two non-obvious behavioral facts: no outbound GitHub call (stale/cached data implications) and no credentials in the response. It stops short of saying how stale the cached commit status may be or what happens if no installation exists.

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?

Two tight sentences, front-loaded with what is read and immediately followed by the two behavioral caveats that matter. 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?

With no output schema, the description effectively enumerates the returned data (installation, selected repos/folders, cached commit status) and discloses the no-credentials/no-request guarantees. The remaining gap is the undocumented parameters and the lack of routing guidance among the many github_* siblings.

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 0% and the description never mentions either required parameter. The meaning of 'company' (UUID) and 'environment' (staging/production) is left entirely to the schema's type/enum, so the description adds nothing about how these scope the returned installation.

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 (read) and a concrete composite resource: the GitHub installation, selected repositories/folders, and cached commit status. It is clearly a read of connection state, but it never distinguishes itself from close siblings like summer_github_sources_read, summer_github_repositories_list, or summer_github_folders_list, so an agent must guess which surface holds what.

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?

"Makes no GitHub request" implicitly tells the agent this is the cached/local read path, which is a useful usage cue, but no explicit when-to-use or when-not-to-use versus summer_github_sources_read / summer_github_repositories_list is given. Usage must be inferred.

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