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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, and the description largely restates them ('read-only, stateless, non-destructive'). The one real addition beyond structured fields is the auth requirement (X-RapidAPI-Key or X-SignalTender-Key); there is no disclosure of validation failure behavior, truncation handling for oversized text, or rate limits, despite the 'strictly validated' claim.

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 core extraction statement is front-loaded, but the description is one dense run-on block with visible waste: the four output key names duplicate an existing output schema, the safety profile duplicates annotations, and the 'Use this tool when executing ... workflows' clause is tautological. The regulatory grounding (DFARS 227.71, DoD 5010.12-M, ASSIST) and character limits are worth keeping, but the whole could be roughly half its length.

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 an output schema exists, the description need not explain return values, and it covers input bounds, auth, regulatory basis, and scope comprehensively for a complex compliance-extraction tool. The remaining hole is behavioral edge cases — what happens with under-length/over-length text or when the source contains no CDRL tables — which an agent would want before invoking.

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 100%, so parameter meaning is already carried by the schema, and the description mostly repeats it ('accepts 15 to 45,000 characters'). It does add a small amount of semantics by explaining that the two context parameters 'calibrate the regulatory regime and threshold assumptions,' which clarifies their role beyond their defaults. That is baseline-plus, not materially above it.

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?

States a specific verb and resource ('Extract all Contract Data Requirements List (CDRL / DD Form 1423) items from DoD RFPs') and enumerates the extraction targets (DIDs, Block 4 authority, submission frequencies, inspection/acceptance codes) plus the derived WBS Data Delivery Calendar. That is precise enough to distinguish it from the two named siblings without opening either schema.

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?

Explicitly routes to alternatives with conditions: 'use scan_far_dfars_clauses instead for general FAR/DFARS clause flow-down audits, or generate_compliance_matrix for general Section L/M shall requirement extraction.' The circular filler sentence 'Use this tool when executing DoD CDRL ... workflows' adds nothing, but the sibling routing is genuinely usable.

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