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

Goes well beyond the annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false) by disclosing admin-only authorization, the SSRF policy that refuses private/link-local URLs, the refusal of plaintext secrets with the required ${SECRET_SLOT:<id>} sentinel flow, and the post-registration gating via grant_mcp_tool. These are exactly the behavioral facts an agent could not derive from structured fields.

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?

Purpose is front-loaded in the first clause, followed by access precondition, then routing guidance, then the two hard constraints and the lifecycle note. Every sentence carries a distinct, non-redundant requirement; nothing repeats the schema or annotations.

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 supplies what an agent needs for this mutation: authorization, URL constraints, credential handling, default tiering, and the follow-up tool for activation. For a 10-parameter registration tool with a linked catalog and secret workflow, that is complete.

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 baseline is 3; the description adds real meaning beyond the schema by explaining the adapter_key-versus-custom decision, the sensitive-key refusal on env values, and the default read_only tier. It does not cover allowed_tools or cluster_allow_list beyond what the schema already says, so it is not a 5.

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?

Opens with a specific verb+resource ("Register an external MCP tool server for the organisation") that is unambiguous against siblings such as list_mcp_servers, get_mcp_catalog, set_mcp_server_enabled and grant_mcp_tool. An agent knows immediately this is the creation path and not a read/toggle/grant operation.

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?

Gives an explicit branching rule: prefer a curated integration by calling get_mcp_catalog and passing adapter_key, and omit adapter_key for a custom server. It also states the prerequisite for usability (tools become callable only after grant_mcp_tool) and the access precondition (organisation admins only), leaving no inference needed.

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