atelierb_read_file

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

With no annotations provided, the description carries the full transparency burden. It goes beyond a generic 'reads a file' by stating 'Content is returned verbatim' and thoroughly explains the .pmi case, including the absence of operation names and the 'po_labels' list. This is strong disclosure for a read operation, though it could have mentioned error behavior or permissions, which are less critical here.

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-loaded, with the main purpose in the first clause. Each of the three sentences earns its place: scope of file types, verbatim return guarantee, and a critical edge-case warning. There is no filler or redundancy.

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 one-parameter read tool with no output schema, the description covers the core behavior, return guarantee, and an important special-case detail. It does not fully specify the return data structure (e.g., JSON wrapper), but for a simple content-retrieval operation, the description is sufficiently complete.

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?

The schema already fully describes file_path as 'Relative path from workspace root to the file' (100% coverage), establishing a baseline of 3. The description adds context about acceptable file extensions, which is helpful for parameter interpretation, but it doesn't fundamentally alter the meaning of the single parameter.

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 opens with the specific verb 'Read' and enumerates the resource types (B source files with extensions .mch, .ref, .imp, etc., C code, Makefile), making the tool's function immediately clear. This distinguishes it from siblings like list_files (which lists names) and write_file (which writes), establishing a clear identity.

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 provides clear context for when to use the tool: whenever file content is needed from the workspace. The special .pmi instruction (do not infer operation names from position) is practical guidance for that file type. However, it doesn't explicitly contrast with list_files or state when not to use it, so it falls short of a full 'when-not' exclusion.

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