edit_fileReplace old_string with new_string in a project file. old_string must match the current content exactly (including whitespace) and be unique unless replace_all is set. Prefer this over write_file for changes to existing files.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| new_str | No | ||
| old_str | No | ||
| projectId | Yes | ||
| new_string | No | ||
| old_string | No | ||
| replace_all | No | ||
| expected_version | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
It discloses the two most operationally important behaviors: old_string must match current content exactly (including whitespace) and must be unique unless replace_all is set. But it is silent on the expected_version parameter's conflict-locking behavior and on failure modes (e.g., what happens when old_string is not found or is non-unique without replace_all). With only readOnlyHint/destructiveHint annotations carrying no safety meaning, the description bears the burden and covers the core but not the conflict semantics.
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 with no filler; the core purpose is front-loaded, the matching constraint follows, and the sibling routing closes it. Every sentence earns its place, though the version/conflict behavior gap means it is not maximally packed.
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 tool with 8 parameters, 0% schema coverage, and no output schema, the description covers the editing semantics well but leaves meaningful gaps: expected_version behavior, failure/error behavior, and the duplicated str/string parameter ambiguity are all unexplained. An agent could call it correctly for the happy path but would not know how it handles version mismatches or non-unique matches.
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 explains old_string, new_string, and replace_all meaningfully. However, it omits expected_version (a version-locking guard that likely carries conflict semantics) and projectId/path, and it does not resolve the schema's confusing duplication of old_str/new_str versus old_string/new_string — a real hazard for an agent choosing parameters.
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 names a specific verb ('Replace... with...') and a precise resource ('a project file'), and it explicitly distinguishes itself from the sibling write_file by instructing agents to prefer it for changes to existing files. This gives an agent enough to separate it from write_file without opening the schema.
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 explicit guidance — 'Prefer this over write_file for changes to existing files' — which routes the agent correctly for the modification case. However, it does not mention apply_patch, another sibling capable of file modification, nor state the when-not-to case (new files) explicitly, though that is cleanly implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Tools are mostly distinct, but there is some overlap among file-modifying tools (edit_file, write_file, apply_patch) and between run_code_in_vm and run_code_in_browser. Detailed descriptions and clearly scoped use cases help agents select correctly.
Most tools follow a verb_noun snake_case pattern (create_project, list_files, execute_sql), but a few deviate (apply_patch, card_upload_asset, run_code_in_vm). Overall readable and predictable, with only minor inconsistencies.
With 46 tools, the server exceeds the typical well-scoped range and approaches the extreme threshold. While the broad scope of a full development platform justifies many tools, this count may overwhelm agents and increase misselection risk.
The tool surface covers the full development lifecycle: project creation, file operations, database management, resource provisioning, deployment, testing, and debugging. Minor gaps exist (e.g., no delete_project or checkpoint management), but core workflows are well-supported.