Retrieves applicable project rules, risks, checks, tests, and callers for specified files before editing, so agents know what to verify first.
What to read and check before changing these files: the project rules and risks that apply, the checks to run, the tests that reach the code and the files that use it. Call it before editing.
| Name | Required | Description | Default |
|---|---|---|---|
| files | Yes | paths relative to the repository root |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations at all, the description carries the full burden. It does disclose the categories of content returned (rules, risks, checks, tests, dependents), which is real value. It says nothing about cost, latency, failure behavior on unknown paths, or the shape/size of the response.
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?
It is a single sentence with no filler, but it is a dense colon-list that front-loads an indirect phrase ('What to read and check before changing these files') rather than the tool's action. The action-bearing instruction arrives last, which is the wrong order for fast scanning.
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?
There is no output schema and no annotations, so the description is the only source of information. It partially compensates by listing content categories, but an agent still cannot tell what the return value actually looks like or how to act on it, which matters for a pre-edit gating step.
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 coverage is 100% and there is only one required parameter ('files', documented as repo-root-relative paths). The description adds only the implicit framing 'these files' and introduces no additional syntax, path conventions, or size expectations beyond the schema, so the baseline 3 applies.
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 conveys the resource indirectly — it enumerates what the tool surfaces (project rules, risks, checks, tests, dependent files) for a set of files. But it never states a verb+resource plainly ('returns a reading list for the given files'), and the name 'read_list' plus the sibling 'changed_read_list' leave the scope boundary unstated. Purpose is inferable but not crisp.
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?
'Call it before editing' gives an explicit trigger condition, which is clear context for when to use it. It stops short of an exclusion or an alternative: nothing says whether to use this instead of 'changed_read_list' or 'check_map', or what to do when files are new/untracked.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.