search_documents

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does state that the tool returns 'complete Markdown sections', which informs the agent about the output nature. However, it omits any details about side effects (probably none since it's a search), error behavior, pagination, or limitations. Since it's a search tool, the read-only behavior is obvious but not explicitly stated. The disclosure is minimal but not misleading.

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 a single, front-loaded sentence with no redundant words. It immediately states the action and the output. This is ideal conciseness – every word earns its place. Nothing is fluff, and it is structured to be read quickly.

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 complexity (three parameters, with an output schema existing), the description is incomplete. It fails to cover parameter semantics, usage scenarios, and behavioral expectations beyond the basic output type. While the presence of an output schema may document the return structure, the description does not help the agent understand when to use the tool or how to fill in the parameters. It is adequate only for recognizing the tool's existence, not for correct invocation.

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%, and the description provides zero information about the three parameters (query, top_k, document_name). It does not explain what the query should contain, how top_k affects results, or what document_name filters. The agent must rely solely on the schema definitions (which have types and defaults but no semantic meaning). The description adds no value beyond what the schema already provides.

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 a specific action ('Search ChromaDB') and a specific output ('complete Markdown sections containing nearby tables and LaTeX equations'). This distinguishes it from sibling tools like list_documents or ingest_document, as it focuses on retrieval of content sections rather than listing or ingesting. However, it could be more precise about the semantic nature of the search and what 'nearby' implies, so not a 5.

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 offers no guidance on when to use this tool versus its siblings. It does not mention alternatives, prerequisites, or scenarios where this tool is preferred. While the purpose implies it's the tool for searching documents, there is no explicit direction such as 'use this to find relevant sections' or 'use list_documents to browse available documents'. This leaves the agent to infer usage context.

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