build_pdf_knowledge_db

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 reveals the tool's use of a local embedding model and the ability to force-rebuild indexes. However, it does not disclose whether the operation is destructive (e.g., overwrites existing data), any authentication requirements, or potential side effects beyond the force_rebuild parameter. The description provides moderate transparency but leaves key behavioral aspects unaddressed.

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 concise and well-structured. It starts with a one-sentence summary of the tool's purpose, followed by relevant technical detail (local model, no API key), a list of example database slugs, and clear parameter documentation. Every sentence adds value without redundancy or unnecessary fluff.

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?

The description covers the main purpose, parameters, and a prerequisite (database must exist via create_knowledge_database()). However, it leaves ambiguity about which PDFs are indexed—there is no mention of input file sources or how PDFs are selected. Given that an output schema exists, return values are not required in the description, but the missing input source is a notable completeness gap for a tool of this complexity.

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?

Given that the input schema has 0% description coverage (no parameter descriptions in the schema), the description compensates effectively. It explains that 'database' is a slug with a default of 'ph-background' and lists example database layers, and it clarifies that 'force_rebuild' controls whether to re-index already processed files. This adds significant meaning beyond the raw schema types.

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 function: 'Index a knowledge database layer from PDFs into the semantic knowledge base.' It specifies the verb (index), resource (PDFs into semantic knowledge base), and highlights the use of a local embedding model, distinguishing it from sibling tools like index_pdf_library or create_knowledge_database. The mention of named layers and the prerequisite of using create_knowledge_database() further clarifies its unique role.

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 some usage context by noting that it uses a local model (no API key required) and that the database slug must be created via create_knowledge_database(). However, it does not explicitly state when to use this tool versus alternatives like index_pdf_library or semantic_search, nor does it include when-not-to-use guidance. The context is clear but lacking explicit exclusions or alternatives.

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