MidOS Research Protocol

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool retrieves a document but doesn't cover critical aspects like whether it's read-only, requires authentication, has rate limits, or what happens on errors. For a retrieval tool with zero annotation coverage, this leaves significant gaps in understanding its behavior.

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 appropriately sized and front-loaded: the first sentence states the purpose clearly, followed by a concise 'Args' section. There's no wasted text, and the structure is easy to parse, though it could be slightly more integrated (e.g., merging the example into the main 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 the tool's low complexity (single parameter) and the presence of an output schema (which handles return values), the description is minimally adequate. However, it lacks behavioral details (e.g., error handling, permissions) and doesn't differentiate from siblings, leaving room for improvement in completeness for a tool in a server with many similar retrieval functions.

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?

The description adds meaningful context for the single parameter 'name', explaining it as 'Truth patch name' and providing an example ('AGENT_MITIGATIONS_CONTEXT_OVERFLOW'). Since schema description coverage is 0% and there's only one parameter, this compensates well, giving clear semantic meaning beyond the basic string type 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 clearly states the tool's purpose: 'Get a specific truth patch document.' It specifies the verb ('Get') and resource ('truth patch document'), making the intent unambiguous. However, it doesn't distinguish this tool from siblings like 'get_eureka' or 'get_protocol'—all appear to retrieve specific documents—so it lacks sibling differentiation.

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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, exclusions, or compare it to sibling tools such as 'search_knowledge' or 'semantic_search' that might handle similar data. Usage is implied only by the tool name and description, with no explicit context provided.

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