read_file

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

Annotations provide readOnlyHint=true, indicating a safe read operation. The description adds behavioral context by specifying that it can read a single file or all files, which goes beyond the annotations. However, it doesn't disclose details like rate limits, authentication needs, error handling, or what 'read' entails (e.g., returns file contents vs. metadata). With annotations covering safety, a 3 is appropriate for adding some value without rich behavioral disclosure.

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 two sentences, front-loaded with the primary action ('Read a file from a project') and efficiently adds the conditional behavior. Every word serves a purpose with zero waste, making it appropriately sized and easy to parse.

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?

Given the tool's moderate complexity (reading files with optional filtering), annotations cover safety, and an output schema exists (implied by context signals), reducing the need to explain return values. The description addresses key usage but could improve by mentioning error cases or limitations. It's mostly complete for a read operation with good structural support.

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%, but the description compensates by explaining the 'name' parameter's role: if omitted, it reads all files. However, it doesn't clarify the 'projectId' or 'codeSourceId' parameters. With one parameter (a nested object) and no schema descriptions, the baseline is low, but the description adds partial meaning for one aspect, warranting a 3.

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 clearly states the verb ('Read') and resource ('a file from a project'), specifying the action and target. It distinguishes from siblings like 'read_object_store_file_download_url' or 'read_project' by focusing on project files. However, it doesn't explicitly differentiate from 'read_file_contents' or similar file-reading siblings that might exist in other contexts, though none are present in the provided sibling list.

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 implies usage by stating 'or all files in the project if no file name is provided,' which gives context for when to omit the 'name' parameter. However, it lacks explicit guidance on when to use this tool versus alternatives like 'list_object_store_files' or 'read_object_store_file_download_url' for different file sources, and doesn't mention prerequisites or exclusions.

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