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

Annotations already declare readOnly/openWorld/idempotent hints, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: federation across three sources, deduplication, ranking remote Streamable HTTP servers first, and an honest disclosure that task_context is 'how this free service learns what agents need.' No contradiction with annotations.

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?

Four sentences, each earning its place: purpose with examples, federation and ranking behavior, return contents, and usage timing. The description is front-loaded with the core purpose and contains zero filler or repetition of schema fields.

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?

With no output schema, the description correctly enumerates the return fields (name, description, URL/package, popularity, last update, install snippet). It also covers sources, ranking, deduplication, and invocation timing. The only minor omission is behavior on empty or failed results, which is not critical for a search tool.

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 the schema already documents all four parameters well and the baseline of 3 applies. The description adds only marginal semantic value: concrete query examples ('postgres', 'wayback machine') and the remote-first ranking behavior that gives context to remote_only. It does not materially deepen parameter understanding beyond the schema.

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 pair ('Search for existing MCP servers') and scopes it to a capability with concrete examples. The federated-source, dedup, and ranking details further distinguish it from the sibling mcp_details, which is clearly about inspecting a single server rather than discovering candidates.

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 gives an explicit when-to-use directive: 'Use before building or asking the user to build a tool.' However, it never mentions the sibling mcp_details or states when the agent should switch from discovery to deep-diving on a specific server, so it lacks an explicit when-not-to-use clause.

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