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

Annotations only declare readOnlyHint=false, idempotentHint=false, destructiveHint=false; the description adds real behavioral context beyond them — that grants are what make tools runnable, and that the server's permission tier gates writes so a write-classified tool never executes under read_only. It does not state whether a grant can be revoked or what happens on re-granting the same tool (relevant given idempotentHint=false), so it falls short of a 5.

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?

Front-loaded with the action and effect, then prerequisites, then the tier caveat, then the recommended sequencing — a sensible order with no filler sentences. The tier explanation is dense and slightly tangential to selecting the tool, keeping it just below a 5.

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 non-idempotent mutation tool with no output schema, the description covers authorization, prerequisites, the tier interaction, and correct sequencing with get_mcp_catalog. It omits reversibility (whether/how a grant is undone) and any indication of the result of the call, which an agent would otherwise have to discover by trial.

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% and all three parameters are documented in the schema, including the 'member' default for allowed_to_role and the max length for tool_name. The description only echoes the 'organisation role' concept and adds no syntax, format, or constraint detail beyond the schema, so the baseline 3 applies.

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?

States a specific verb and resource ('Grant one of a registered MCP server's tools') plus the observable effect ('making it callable from agent runs') and the target of the grant ('an organisation role'). This distinguishes it cleanly from sibling tools like register_mcp_server, set_mcp_server_enabled, and list_mcp_servers without needing the schema.

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 explicit preconditions ('Organisation admins only'), explains why the tool is necessary ('Registration alone offers nothing'), and names an alternative/prior step with its tool ('Grant the adapter's recommended_tools first (get_mcp_catalog) rather than blanket-granting an unknown inventory'). When-to-use, prerequisites, and a discouraged pattern are all covered.

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