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

Beyond annotations, the description discloses the need for confirmation ('Requires confirm: true') and technical safety behavior ('Uses npm pack + tar extraction; no shell interpolation of paths'). It also clarifies the local-mode restriction, which is important for hosted environments. This adds meaningful context to the annotation flags (readOnlyHint false, idempotentHint true).

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 first sentence is direct and informative, but the description then appends a long block of generic 'SAP MCP execution guidance' (pricing, routing, signer boundary) that is not tool-specific. This boilerplate reduces conciseness and adds noise, although the essential tool-specific details are compact.

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?

The description covers the core operation, local-only constraint, confirm requirement, and technical method. However, it leaves key parameters (skills, agent, targetDir) under-specified, and the generic SAP guidance contributes little to this tool's context. An output schema exists, so return values are documented, but the input semantics remain incomplete for correct invocation.

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 effectively 100% in number of parameter descriptions, but those descriptions are tautological ('Agent parameter for...'). The tool description only elaborates on 'confirm' (requires true). It does not explain what 'skills' are (names? file names?), or how 'agent' or 'targetDir' interact. Baseline 3 is appropriate because schema covers the fields, but no additional semantic value is added.

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 a specific verb+resource construction: 'Refresh local agent skill files from the latest published @oobe-protocol-labs/sap-mcp-server package.' This clearly distinguishes it from sibling skills tools (install, check_updates, list, upgrade_plan) by emphasizing 'refresh' and 'local-mode only'. The 'Local-mode only (hosted MCP cannot write to the caller machine)' further clarifies scope.

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 states a key usage constraint: 'Local-mode only (hosted MCP cannot write to the caller machine).' It also states a prerequisite: 'Requires confirm: true.' This tells the agent when the tool is applicable. However, it does not name alternative tools like sap_skills_check_updates or sap_skills_install, so the guidance is good but not fully explicit about when-not-to-use in favor of alternatives.

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