skills_get_reference

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

With no annotations, the description carries full burden. It discloses the two-phase fetch behavior and the conditionality. It implies a read-only operation but does not explicitly state non-destructiveness or mention potential errors. However, the behavior is reasonably transparent for a fetch 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?

Description is concise with two clear paragraphs. Purpose is front-loaded. Could be slightly shorter without losing clarity, but overall efficient.

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?

Given the low complexity and presence of an output schema, description adequately covers usage context, return behavior (manifest vs content), and conditions. Does not address error handling or edge cases, but is comprehensive enough for the tool's simplicity.

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 0%. Description adds meaning for 'filename' (default 'list' and two-phase use) but does not explain 'skill_id'. Partially compensates for the lack of schema descriptions, but not fully.

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 clearly states it fetches a reference document bundled with a skill, specifying file types (checklists, policies, API specs, examples). It implies being part of a sequence (STEP 3a) but does not explicitly differentiate from sibling tools like skills_get_asset, which may also fetch files.

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?

Explicitly states when to call: only when tier3_manifest from skills_get_body lists reference files and skill instructions name one. Also warns against speculative loading. Two-phase usage is clearly described.

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