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

Annotations already declare read-only/idempotent behavior, but the description goes further by revealing exact mechanics: BGE-base-en embeddings, cosine similarity, 500-char overlapping windows, a 200K char cap with truncation flag, and return contents (offsets, similarity scores). This substantially exceeds the annotation baseline.

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 front-loaded with the core action and use case, and every subsequent clause adds operational detail. It is somewhat long, but all information (algorithm, limits, pairing) is relevant to correct invocation rather than padding.

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?

Despite lacking an output schema, the description directly states what the caller receives: top-N passages with character offsets and similarity scores. It also covers input limits and truncation behavior, making it sufficient for an autonomous agent to invoke the tool 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?

The input schema already documents all three parameters with 100% coverage. The description adds concrete usage context—examples of appropriate text (SEC 10-K body) and query phrasing—that enriches comprehension without needing to restate schema details.

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 opens with a specific verb phrase, 'Semantic search INSIDE a fetched record,' and clearly defines inputs and outputs. It distinguishes itself from the sibling ask_pipeworx_grounded by explaining the intended pairing, making its unique role unambiguous.

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 an explicit trigger: 'Use when the record is too big to cram into the prompt' and explains the context-saving benefit. It names a companion tool (ask_pipeworx_grounded) and contrasts grounding over relevant passages vs. the whole document, though it does not state explicit non-use cases.

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