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

Annotations already cover read-only, idempotent, non-destructive behavior, so the description's job is to add context, which it does by clarifying that data comes from cache and requires no credentials. However, it doesn't describe truncation, size limits, offset/paging behavior, or what happens on an invalid path, and 'No live GitHub call' sits in mild tension with openWorldHint=true.

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 short sentences, front-loaded with the dual behavior, followed by availability scope and safety note. Nothing is padded or repeated.

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 read-only cached tool with annotations covering safety, the description plus a mandatory 3-param schema gets an agent most of the way. But with no output schema, it never states what is returned (path list vs file contents, and how offset affects results), leaving a real gap for the read mode.

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%, so the description must carry parameter meaning, but it only explains the role of 'path' (trigger for read mode). company, environment, source_id, and especially offset are entirely undocumented; the sentence about selected company folders only loosely hints at 'company'.

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 concrete verb+resource in both modes: list cached source paths, or read one cached file when a path is supplied. The 'cached' qualifier separates it conceptually from summer_github_sources_sync and summer_github_folders_list, though neither sibling is named explicitly.

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?

The mode-switching rule (no path = list, path = read a single file) is implicit in the phrasing and gives some usage direction. It does not say when to reach for this versus summer_github_folders_list or summer_github_sources_sync, and there are no explicit prerequisites or exclusions beyond the company-folder constraint.

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