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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds real context beyond that: the explicit-user-request policy and the failure mode 'Returns mmp_not_enabled while MMP is not enabled for the tenant', which tells the agent how to interpret an error.

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?

Three short sentences, front-loaded with the action, then the safety constraint, then the error behavior. Every sentence earns its place with no filler.

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?

There is no output schema, so the description reasonably omits return details, and it covers the destructive nature and one error code. For a destructive delete whose two parameters are entirely undocumented, though, the meaning of connection_id and connection_context is missing.

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 0% for two parameters, so the description must carry the load and it does not. It never explains what connection_id identifies versus the connection_context token (pattern ^mctx_v1_[0-9a-f]{64}$) or whether the latter is optional scoping; only 'one MMP connection' hints at the target.

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 gives a specific verb and resource: 'Delete one MMP connection on the Meta-owned MMP service', scoping the action to a single connection. It is unambiguous against siblings like mmp_get_state, mmp_refresh_connection and mmp_save_cohort_config, but it does not explicitly differentiate itself from them, which caps it at 4.

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?

'Destructive write; call only on explicit user request' states a clear precondition for invocation, which is exactly the kind of gating guidance a mutating tool needs. It does not name alternatives (e.g. mmp_refresh_connection) or say when-not to use it beyond the user-request gate, so it stops short of 5.

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