files_browse

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

Annotations already declare readOnlyHint=true, so safety is covered. The description still adds real behavioral context: the default path target and the allowed-root restriction that determines whether a browse will be rejected. It omits return ordering, pagination, and what an out-of-root error looks like.

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 short sentences, front-loaded with the core action and return content, then defaults and constraints. The kind mapping is the only detail worth its length; the blank-line-wrapped formatting is slightly awkward but wastes no words.

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 2-parameter, read-only listing tool with no output schema, the description covers action, return contents, default argument behavior, and the access boundary. Reasonably complete; it just lacks return-shape and error-condition detail that an agent navigating a file tree might want.

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 there are no enums, so the description carries the full burden — and it largely does: it maps kind="sql" to .sql files and kind="notebook" to .ipynb files, and explains that path defaults to the SQL folder. It stops short of specifying path format (absolute vs relative) or what values kind accepts beyond the two examples.

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 ("List a folder for the file browser") and enumerates exactly what is returned: subfolders plus .sql or .ipynb files filtered by `kind`. That is precise enough to picture the operation, though it never names a sibling tool it should be preferred over.

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?

It gives useful context ("`path` defaults to the SQL folder") and a hard precondition (only folders inside the user's home, the SQL folder, or SINGLESTORE_MCP_FILE_ROOTS can be browsed), which tells the agent when calls will succeed. But it never says when to pick this over notebook_files / sql_editor_files or what to do instead, so usage is implied rather than stated.

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