skill_file

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

Annotations already declare readOnlyHint and idempotentHint, so the description carries a lighter burden. It adds valuable behavior beyond annotations: relative-path scoping and type-dependent return encoding (text as text, non-text as base64 with media type). No contradiction with the annotations.

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 sentences, each adding distinct information: the operation, path resolution and return encoding, and batching guidance. The purpose is front-loaded and there is no filler or redundant restatement.

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 read-only, two-parameter tool with no output schema, the description covers purpose, path scope, return encoding, and batching, while the schema covers parameter details. The only notable gap is that the response shape for multiple requested paths is not spelled out.

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 100% and the parameter descriptions already document provenance ('exactly as skill_list reports it', 'as skill_load lists it') and the batching/round-trip rationale. The description mostly repeats the relative-path constraint, so it adds little parameter meaning beyond what the schema already provides.

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 names a specific verb and resource ('Read files a skill bundles') and clarifies that paths are resolved relative to the skill's directory, so the tool's role is clear. It does not explicitly distinguish itself from skill_load, but the read-file intent is unambiguous among the sibling 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?

The description gives explicit batching guidance: 'Ask for every file you need in ONE call' and explains why with 'a SKILL.md usually points at several.' It provides clear context for efficient use, though it relies on the schema's parameter descriptions to point the agent to skill_list and skill_load rather than stating alternatives directly.

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