knowledge

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

No annotations existed, so the description carried the burden. However, the description fails to explain behavior like parameter orchestration, dispatch behavior, return format, or side effects. Saying 'entrypoint for consult/export' does not reveal what happens when the agent calls it.

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 two sentences, which is concise, but the second sentence is about backward compatibility and does not clearly describe the tool's function. It could be more direct about the tool's purpose and parameters.

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?

Complexity is high with 11 parameters, routing to sub-operations, and sibling tools relying on this entry point. The description does not address required 'op' values, parameter validation, error behavior, or the format/meaning of the response. With all field descriptions missing, the natural language must be much richer to be 'complete', but it is not.

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?

Since the schema description coverage is zero percent and most parameters like 'op', 'mode', 'limit' have no defaults, the description should compensate, but it does not explain what each parameter does. The construction of 'op' values or the meaning of 'mode' is not elaborated. Given the zero coverage, the description provides no additional meaning beyond what is in 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?

The description calls it a 'Consolidated knowledge-graph entrypoint' which is vague, though it does reference 'consult/export' operations. It fails to state what distinct operation the tool performs or what it creates. The title is null, and the tool name 'knowledge' is broad, which is unhelpful.

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?

It says existing tools 'remain registered', implying a consolidated interface, but it doesn't explain when to use this tool versus the specific siblings like 'query' or 'export'. It suggests clients prefer explicit tool names, but doesn't clarify if the agent should invoke this tool as a router. The second sentence does note that alternatives exist for clients preferring explicit tool names, which provides some guidance that this is a wrapper.

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