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

Annotations already declare readOnlyHint=false, destructiveHint=true and openWorldHint=true, so the safety profile is known. The description adds a genuinely non-obvious protocol detail — irreversible endpoints require {"confirm": true} in the body — which is not visible anywhere in the schema. It says nothing about auth requirements, rate limits, or how errors/unknown paths surface, which matters for a fully open passthrough.

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 with no filler: scope first, then the hidden protocol requirement, then the user-confirmation guardrail. The ordering puts the highest-value information (when to use this instead of siblings) at the front.

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 dangerous open-world passthrough this covers the essentials: scope, path discovery route, the confirm flag, and a human-in-the-loop rule. Remaining gaps are what a caller gets back and how failures on non-existent paths behave (there is no output schema to carry that), which is a modest omission rather than a blocking one.

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 80%, so the baseline is 3; the description earns above that by documenting a body sub-key ('confirm': true) that the free-form 'body' object schema cannot express. It also adds the /bridge/v1 path convention context, though the waba_id and query semantics are left entirely to the schema.

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 ('Call any WasapFlow Bridge endpoint') and immediately bounds the scope to endpoints 'not covered by the other tools', which is exactly the distinction an agent needs against the 14 siblings. It also names a sibling (bridge_docs_search) as the place to resolve paths, so the tool is separable from the dedicated tools without opening any 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 a clear when-to-use rule (only endpoints the dedicated tools don't cover) and points to bridge_docs_search as the alternative for discovering paths, plus a precondition to confirm with the user before mutations. It stops short of enumerating which sibling tool covers which operations, so the agent must infer that preference ordering.

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