knowledge_code

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

Annotations carry the safety profile with destructiveHint=true and readOnlyHint=false, so the agent is warned that this tool can be destructive. However, the description adds no behavioral context about what gets destroyed, when side effects occur, or how fallback behavior works. The word 'fallback' hints at one behavior but is not explained.

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 extremely short, which is concise, but it is under-specified rather than efficiently structured. It is not a sentence, provides no front-loaded action, and leaves the agent to infer meaning from the schema. This is closer to a set of tags than a usable description.

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?

Given 14 parameters, 9 possible actions, a destructive hint, and seven sibling tools, this description is radically incomplete. An agent cannot determine which action to invoke, what parameters are relevant, or what safety caveats apply. The output schema helps with return values, but the lack of contextual guidance makes the tool very hard to use correctly.

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 only 7%, and the description does almost nothing to compensate. It names 'symbols' and 'callers', which loosely map to the symbol and references actions, but it provides no meaning for the many parameters such as path, kinds, query, symbol_id, resource_uri, or fallback_result_paths. This is insufficient for a 14-parameter tool.

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 is a fragment: 'Code index, symbols, callers, fallback.' It names the tool's domain but uses no verb and does not state what the tool actually does. It is not a tautology, but it is far too vague to convey a clear purpose or distinguish it from sibling tools.

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?

There is no guidance on when to use this tool versus siblings like knowledge_context or knowledge_page. No conditions, exclusions, or alternatives are mentioned. The action enum in the schema gives per-action hints, but the description itself provides zero usage direction.

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