Read up to 400 numbered lines from one staged project file, bounded to 12 KB. Returns its current hash for exact patches. Default reads 160 lines. Follow nextRead (startLine/startColumn) to read omitted source, including long minified lines. Never guess omitted code.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| endLine | No | ||
| startLine | No | ||
| startColumn | No | ||
| workspaceId | Yes | ||
| codeWorkspaceId | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive, yet the description adds substantive behavior beyond them: hard caps (400 lines, 12 KB), the default window (160 lines), the returned content hash, nextRead continuation semantics for omitted/minified lines, and an explicit anti-hallucination instruction.
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?
Five dense clauses, each carrying distinct information (scope, bounds, hash, default, continuation). Front-loaded with the read action and cap; no filler or restated title.
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?
Annotations cover the safety profile and there is no output schema, so the description appropriately explains what comes back (numbered lines, hash, nextRead). The gap is that with 6 parameters at 0% schema coverage, the agent still gets no guidance on the two workspace IDs or path validation.
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% across 6 parameters, so the description must carry the burden. It only indirectly explains startLine/startColumn via the nextRead mention; workspaceId, codeWorkspaceId, path, and endLine semantics (e.g. ranges, precedence vs default) are entirely undocumented.
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+resource ("Read ... numbered lines from one staged project file") and qualifies scope with size bounds, so the agent knows this is file-content retrieval rather than search or patch. It does not explicitly name siblings like search_world_code or apply_world_code_patch, but the "for exact patches" phrasing implicitly positions it against the patch tool.
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?
Provides operational guidance ("Follow nextRead ...", "Never guess omitted code") that tells the agent how to consume the result, which implies the read-then-patch workflow. However it never states when to use this versus alternatives such as search_world_code or inspect_world_code_workspace, so usage context is only 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.
