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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, not open-world), so the bar is lower, yet the description still adds real behavioral facts: reads are confined to the default branch, and a directory path silently switches to entry-listing mode. That mode switch is non-obvious and would otherwise surprise a caller. Missing: error behavior for nonexistent paths or truncated/large files.

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 sentences, zero filler, and the primary file-read contract is front-loaded ahead of the directory-listing exception. Nothing is padded.

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 and only two parameters, the description supplies what an agent needs to call it correctly: default branch, default file, and directory-mode behavior. Return format and error/truncation behavior are left unspecified, but for a low-complexity read tool this is close to sufficient.

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 50% (the repo param is documented, path is not), so the description must compensate, and it does: it explains what `path` means by default and that it changes behavior when it points at a directory. This adds semantics beyond the bare schema default of README.md.

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 and resource ('Read one file') plus the scope constraint that it comes from a switched-on repo's default branch. The dual behavior (file vs directory listing) is spelled out. It does not name the sibling it is not — e.g. list_github_repos or get_github_change — so differentiation is implicit rather than explicit.

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?

'By default the README, which is the quickest way to learn what a product is' gives a motivation for a common usage but does not state when to prefer this over list_github_repos, list_github_changes, or get_github_change. Usage is implied rather than routed.

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