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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the bar is lower; the description still adds real behavioral context: results are relevance-ranked, the returned score is a 0-1 relevance value explicitly NOT a DCPI score (prevents a likely misinterpretation), and the cite fields are itemized by source type. It does not discuss pagination or cost/latency for the all-corpora default, which keeps it short of a 5.

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?

Front-loads the decisive routing rule in the first sentence, then examples, then params, then return shape and sibling comparisons — a sensible information order with no filler sentences. It is still one dense paragraph of near-maximum length, which costs it a point on structure.

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?

An output schema exists, yet the description still gives a compact return shape ({results:[{source_table, kind, text, score, cite}]}) and explains the only ambiguous field (score). Combined with the corpus defaults, alias rule, licensing/citation instruction, and sibling disambiguation, an agent has everything needed to call this 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?

Schema coverage is 100%, so the baseline is 3; the description goes beyond it by giving defaults (corpus=all, k default 8), the 1-15 bound, the natural-language intent of q, and the q/query alias rule ('send exactly one'). One flaw: the description's corpus list (press_releases, announcements, permitting_intel, construction_permits, tax_incentives, capacity_pipeline, facilities) does not match the schema's enumerated values (news_articles, deals, discovered_facilities, market_narratives), which could lead an agent to pass a value the schema does not declare.

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 opening clause names the exact operation (meaning-based retrieval) and the discriminating condition (conceptual/fuzzy questions where keyword filters fall short), then enumerates the corpora covered. It cleanly separates itself from the exact-filter siblings (get_news, list_transactions, search_facilities) and from get_market_context, so an agent can route without opening a 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?

Explicit when-to-use ('CONCEPTUAL / fuzzy questions where keyword filters fall short'), explicit alternatives with the condition that selects them (exact-filter tools vs. this relevance-ranked tool; get_market_context for a token-budgeted briefing), and three worked query examples that show the intended call shape. Nothing is left to inference.

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