list_repository_tree

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

Annotations declare readOnlyHint=true and destructiveHint=false, which are matched by the description's 'Read' framing. The description adds valuable behavioral context beyond annotations: the fact that paths are 'untrusted repository content' and that recursive result truncation can occur. This security warning and truncation disclosure are genuinely useful additions beyond what the annotations provide.

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 sentences, zero filler. Front-loaded with the core purpose, followed by security and truncation caveats. Every sentence carries meaningful information about behavior or constraints.

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 8 parameters but no output schema, the description covers the key operational concerns: pagination (limit/offset implied by 'bounded page'), recursion truncation behavior, and path security. The security warning is particularly important for a tool that returns untrusted content. Slight gap: no detail on what the returned tree structure looks like, but for a read-only listing tool this is acceptable given the annotations already establish safety.

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 only 13%, so the description should compensate. The description effectively communicates the recursive/limit/offset semantics through its truncation and 'bounded page' language. However, it doesn't detail individual parameters like path, limit, or offset semantics beyond what the schema's type/default constraints provide, so it doesn't go far beyond baseline schema meaning.

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?

Description specifies it reads 'committed files, directories, symlinks, and submodules' from 'a branch, tag, or commit in an allowed repository' - a specific verb (read), resource (repository tree), and scope (bounded page, committed content). It distinguishes itself from siblings like get_branch, get_repository_file, and commit_files through its tree-listing purpose.

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 description states that recursive results 'can be truncated by GitHub' and that 'non-recursive subtree traversal remains available for complete inspection,' giving clear practical guidance on when to use recursive vs non-recursive modes. It could explicitly name alternative tools (e.g., get_repository_file for individual files), but it provides effective usage context for the main use case.

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