Decide which MCP tools to use

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds real behavior beyond that: the response contains scores, priority tiers, and 'deterministic reasons', and an empty recommendation set is a valid outcome. It omits how discovery interacts with the available_mcp_servers override, but the core behavior an agent needs to decide is disclosed.

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 short sentences, front-loaded with the action and followed by the call trigger and the empty-result caveat. No filler, though the output-shape sentence could be trimmed since it partly restates the name.

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?

There is no output schema, and the description only partially compensates by naming the return fields. With nested, sparsely documented parameters and a routing role that overlaps several siblings, an agent still lacks guidance on context/options usage and on how this differs operationally from check_tool_need.

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 only 33% and the schema is nested (context.project_type, context.working_directory, options.threshold, options.max_recommendations), yet the description never mentions context or options at all. Only user_query is effectively covered, via the schema's own 'The user task to route' and the phrase 'Analyse a user task', leaving the tunable threshold and recommendation cap unexplained in both places.

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?

States a specific verb ('recommend') and resource ('available MCP tools') and describes the output shape (scores, priority tiers, deterministic reasons), which separates it from catalog/audit siblings. It does not name which sibling to prefer over systemone_check_tool_need or systemone_analyze_task, so the differentiation is inferable rather than explicit.

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?

'Call this before complex or multi-step tasks' gives a clear trigger condition, and 'Returns no recommendations when the task needs no external tool' tells the agent the negative case exists. It stops short of naming alternatives for simple single-tool tasks, so the exclusion is implied rather than stated.

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