inspect_projectReads package.json, package-lock.json, and components.json to generate a HostProfile with evidence, enabling UI stack recommendations without executing code.
Read bounded package.json, package-lock.json and components.json within the server working directory. Return a HostProfile with evidence; never execute project code.
| Name | Required | Description | Default |
|---|---|---|---|
| relative_path | No | . |
Changes observed during successful MCP inspections.
v0.4.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover readOnlyHint, idempotentHint, destructiveHint, so the description's job is lighter. The description adds value beyond annotations by naming the explicit file set, stating that it returns a HostProfile with evidence, and clearly declaring it never executes project code. A point is lost for not adding detail on what 'evidence' includes or path constraints like symlink handling.
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 sentences, zero filler. The first sentence states the capability and deliverables; the second adds the critical safety constraint. No repetition of schema or annotations, and the structure is front-loaded.
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-only tool with annotations covering safety and idempotence, the description is complete enough. A little more detail on the returned HostProfile shape or 'evidence' would be useful given there is no output schema, but the tool's simplicity and the 'never execute' disclaimer make it adequate.
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 semantics must come from the description. The description implicitly associates relative_path with the working directory via 'within the server working directory', but it does not explicitly explain that relative_path selects a subdirectory or that 'bounded' prevents escape. Since there is only one parameter, the description mostly compensates but still does not fully clarify relative_path semantics.
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 states a specific verb ('Read'), names the exact resources ('bounded package.json, package-lock.json and components.json'), and defines the scope ('within the server working directory'). It also distinguishes from siblings by being the only read/metadata tool among the listed alternatives.
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 clearly communicates what the tool covers and does not cover: only the three named files, and no code execution. This gives an agent a strong signal for when to use it and what it cannot do. It does not explicitly name sibling alternatives to defer to, but given the sibling list, no alternative clearly overlaps with this read function.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.