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

The description discloses the crucial non-obvious trait: despite the word 'Add', the tool only returns configuration and the actual install is deferred until the user signs in. It also reveals the conditional result modes (purchase_required, needs_input) and the exact contents of the returned config. This aligns with readOnlyHint=true and adds substantial value beyond the annotation.

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 purpose is front-loaded in the first sentence, and each subsequent sentence carries a distinct, valuable detail (return items, entitlement rules, error outcomes, config-only caveat). At five sentences it is longer than the minimum, but the density of behavioral nuance justifies the length.

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 entitlement rules, free vs paid scenarios, unknown slug handling, return contents, and the fact that installation is deferred to sign-in. Together with the existing output schema and annotations, an agent has all needed information to decide when and how to invoke this tool correctly.

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 slug's schema description already identifies it as a published agent slug from findagent_browse_agents. The tool description adds context about slug use in the URL and validation behavior, but no additional syntactic or formatting details for the parameter itself. With full schema coverage, baseline 3 is appropriate.

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 states a specific verb ('Add'), resource ('published FindAgent agent'), and scope ('entitled to'), and details what the tool returns. It distinguishes itself from findagent_browse_agents and findagent_buy_agent through the conditional routing of results, but it does not explicitly contrast with the similarly named findagent_create_remote_mcp, so it stops short of full sibling differentiation.

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 provides clear context for when to call this tool: the agent must be published and the caller entitled (free or paid/purchased). It also routes edge cases to alternatives ('purchase_required' points to findagent_buy_agent; 'needs_input' points back to findagent_browse_agents), effectively giving condition-based guidance. It lacks an explicit exclusion like 'do not use for arbitrary remote MCP servers', which would make it a 5.

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