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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered by structured data. Beyond that, the description adds genuine context by disclosing the payload scope — SKILL.md plus its reference files — but says nothing about the volume of that payload or how multiple files are returned, which matters for a bundle-style read.

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 compact sentences: what the resource is, what the two variants are, then the operating instruction and install command. Nothing is padded, and the core identity is front-loaded, though the trailing install command is loosely attached and slightly dilutes the close.

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 single-parameter read with no output schema, the description covers intent and variant meanings well enough to call it. The gap is that, absent an output schema, it never says how the returned playbook and reference files are shaped or bounded, which an agent needs to know before consuming them.

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% and the single parameter carries an enum with a generic "Skill name." note, so the baseline would be 3. The description earns above baseline by actually explaining what each enum value covers — terudo-elements as the eSIM offer embedded in web pages, terudo-api as server-side API and webhooks — letting the agent pick correctly without further lookup.

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 resource — the full playbook (SKILL.md plus reference files) for integrating Terudo — and enumerates the two retrievable skills. It does not differentiate from close-sounding siblings such as api_reference, elements_snippet, or read_doc, so an agent cannot be fully certain which of those to prefer.

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?

It says to "follow its rules and checklist" and gives an install command (`npx -y @terudo/cli skills add`), which implies how the retrieved content is meant to be consumed. However, there is no explicit when-to-use-this vs. when-to-use api_reference / read_doc guidance, and the install line sits ambiguously between being an alternative retrieval path and a follow-up action.

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