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

Annotations already declare read-only, idempotent, non-destructive behavior, and the description reinforces that with "Nothing is stored" while adding genuinely new facts: the 50-file-per-call cap and the crucial workspace scoping rule that "not found" means not present in this call, not absent from the server. It does not describe the shape of the validation report, which is a remaining gap.

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?

Front-loads the verb and resource, then layers the constraints in descending importance. It is a single dense paragraph with some embedded parenthetical examples, but no sentence is filler.

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, stateless validation tool with no output schema, the description covers inputs, limits, and the semantics of a not-found result. The only real omission is what a returned validation report contains (error list, severities), which an agent would want before parsing results.

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 the baseline is 3; the description earns above that by explaining why `path` matters (it determines the file's type), giving a concrete example path, and clarifying that the `files` array is a single coherent set whose members cross-reference each other.

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?

Names a specific verb and resource ("Validate plugin config files (YAML and Lua)") and enumerates the checks performed: required fields, allowed values, plugin rules, Lua analysis, and cross-file references. It is clearly distinct from the fetch/search siblings, but it never distinguishes itself from `validate_lua_power_draft`, whose scope (Lua analysis) visibly overlaps.

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?

Gives concrete operational guidance: send every file with its full server path so the type can be inferred, batch related files together because cross-references resolve only within the sent set, and stay under 50 files. It stops short of naming an alternative tool or stating when to prefer `validate_lua_power_draft`.

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