read_skill_file

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

ReadOnlyHint already establishes this as a read-only operation, and the description adds useful behavioral detail: it performs progressive disclosure, keeps context lean, and advises reading a script before running it. This goes beyond the annotation without contradicting it.

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?

The description is well-structured with a purpose sentence and an Args section. It is slightly longer than strictly necessary but every sentence adds value—progressive disclosure guidance, the relationship to get_skill, and a script-running note. No fluff, but it could tighten the phrasing.

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?

Without an output schema, the description gives enough context for the expected file-loading behavior, points to get_skill for the file list, and clarifies path aliases. It does not explicitly describe the return format or error cases, but for a read-only file loader with readOnlyHint, this is reasonably complete.

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?

The description explains skill_id (user/... or project/... for editable skills) and path (file path within the skill), plus notes file_path as an alias. However, the config parameter is completely undocumented, and schema description coverage is 0%, leaving at least one parameter's semantics unclear.

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 opens with 'Load one reference/data file of a skill, on demand (progressive disclosure)', which clearly identifies the verb (load), resource (reference/data file), and scope (within a skill). It also distinguishes itself from get_skill by positioning it as the complementary per-file loader.

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 explicitly explains when to use this tool: after get_skill() returns the SKILL.md contract and the list of files, call this to load a specific file only when needed. It also names the sibling tool get_skill and even provides an example path convention, giving clear usage context and differentiation.

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