list_restart_files

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

No annotations are provided, so the description carries the full behavioral burden. It implies a read-only listing by saying 'with sizes and times', but does not state whether the operation is safe, whether it modifies the filesystem, or what permissions are needed. A bare 'Restart files...' does not explicitly declare read-only behavior.

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?

The description is compact and front-loads the key information about what files are listed. The trailing 'Args: directory' is terse but functional; no unnecessary sentences are present.

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 simple one-parameter listing tool with an output schema that covers return values, this is minimally adequate. However, it leaves the directory parameter meaning vague and makes no explicit statement about read-only safety, which an agent would need when calling a filesystem-touching tool.

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 compensate. It only says 'Args: directory', which essentially repeats the parameter name without adding format, expected location, or whether it should be an absolute path. The phrase 'a run left in its folder' hints that directory is the run folder, but that is too implicit to count as adequate semantic coverage.

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 gives a precise resource ('restart files a run left in its folder') and enumerates the specific file patterns (d3dump*, d3full*, dynain, dynain.lsda) that will be listed, adding useful domain specificity. It does not explicitly contrast itself with sibling tools like list_solver_files, so it stops short of the 5 criterion.

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?

Usage is implied by the phrase 'restart files a run left in its folder' and the note that dynain is 'initial state for a follow-on analysis', which suggests when the tool is relevant. However, there is no explicit 'use this when' statement or exclusion of alternatives, so guidance is only inferred.

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