retrieve_tools

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

The description implies a read-only discovery operation, but annotations declare destructiveHint=true, creating a contradiction. No explanation of why destructiveHint is set; this undermines trust. The description does not disclose any destructive behavior.

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 front-loaded with the most critical instruction ('CALL THIS FIRST') and provides structured details. While somewhat lengthy (8 sentences), each sentence adds useful information like BM25 search, quarantine exclusion, and server addition workflow.

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 tool's role as a discovery mechanism, the description covers when to use it (always first), what results include, and related tools. However, it omits aspects like error handling, pagination for large result sets, and behavior when no tools match. The contradiction in annotations is not addressed.

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%, so parameters are well-documented in the schema. The description adds minimal value beyond repeating the natural language usage for the query parameter. No additional context for debug, explain_tool, include_stats, or limit beyond what the schema provides.

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 the tool's purpose: discover relevant tools using BM25 search. It specifies the verb ('CALL THIS FIRST') and resource ('tools across all upstream MCP servers'), and distinguishes itself from sibling tools like call_tool_read/write/destructive.

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 says 'Always use this before attempting to call any specific tools.' Provides guidance on natural language queries, explains results include annotations and call_with recommendation, and tells agents to use recommended variant. Also mentions quarantined servers and links to related tools for adding servers.

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