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

Annotations declare readOnlyHint=true and destructiveHint=false, so the safety profile is already covered. The description adds substantial behavioral context beyond annotations: it performs a real MCP handshake, writes SKILL.md from the server's own tool roster, configures a runnable harness, flags needs_key for 401/403, and is owner-scoped with refresh-on-rerun. It also discloses that secret_alias is resolved server-side and never written into params or a trace. The only minor gap is that it doesn't explicitly state the return value shape, but no output schema exists and the description covers the key behaviors.

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 dense and information-rich, with the core value proposition front-loaded ('FREE, permanently, on any account including the free tier'). Every sentence adds meaningful information. It loses one point for being somewhat long and run-on in places, with the parenthetical about SKILL.md being a bit convoluted. But it is well-structured overall with the key flow described first and auth requirements at the end.

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?

For a 5-param tool with no output schema, the description is remarkably complete. It covers the full pipeline (SSRF screen, handshake, SKILL.md generation, publishing, harness), edge cases (401/403, needs_key), ownership semantics, refresh behavior, post-listing endpoints (/probe and /call), and auth requirements. An agent has everything it needs to decide whether to call this tool and what to pass.

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 100%, so the schema already documents all 5 parameters. The description adds meaning beyond the schema: it explains that endpoint must be a streamable-http endpoint, that name defaults to the endpoint's host, and that secret_alias is resolved server-side and never written into params or a trace. It also clarifies the 401/403 needs_key behavior which relates to secret_alias. This goes beyond the baseline 3 for full schema coverage.

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+resource: 'Put a remote MCP server in front of every agent that searches Rokha' and 'publishes the registry listing'. It clearly distinguishes this from siblings like registry_publish, registry_search, and wall_mcp_publish by describing the full one-call flow (SSRF screen, MCP handshake, SKILL.md generation, harness config).

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 says when to use it: 'Pass the streamable-http endpoint and Rokha does the rest in ONE call'. It also gives exclusions/edge cases: 'A server that answers 401/403 still lists... the reply flags needs_key instead of pretending the server is dead'. It names the auth prerequisite and how to mint a JWT, and mentions re-running the same name refreshes the listing. This is strong usage guidance.

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