code_files

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

With no annotations, the description carries the full burden; it does disclose the backing sources (PkgSeer + jsDelivr) and the registry restriction, and 'List' implies a read-only operation. However it says nothing about recursion depth, pagination/truncation for large packages, or auth/rate-limit behavior, which matters for a listing tool.

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 short clauses, front-loaded with the action and resource, then constraints, then an example. No filler sentences; every phrase carries information.

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 two-parameter listing tool with full schema coverage and no output schema, the core invocation info is present. The remaining gaps — whether listing is recursive, how results are shaped or limited, and what an empty result means — leave the agent guessing at behavior after the call.

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%, so both parameters are already documented; the description only reinforces them via the example 'code_files(spec='npm:express')' and the 'npm:express/src/' path form. That illustrates how spec and path combine but adds little beyond the schema text.

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 and resource — 'List files in an indexed dependency' — and scopes it to a package path, with a concrete example call. It is distinguishable from siblings like code_read or searchcode by being a directory-listing operation over an indexed package, though it never explicitly contrasts itself with those tools.

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?

'indexes npm/pypi/crates ONLY (github: specs rejected)' is an explicit exclusion that prevents a whole class of wrong calls. What is missing is the positive routing: nothing says to use code_read for file contents or searchcode for content search, so the agent must infer the alternative.

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