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), and the description adds substantial behavior beyond them: results are deduplicated to one document per filing, include an excerpt when available, carry SEC's relevance score separately, and honor CIK/date/exact-form filters. It also discloses the 10,000-hit approximation and hard pagination ceiling, which an agent could not learn from the schema or annotations.

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?

Purpose and query semantics are front-loaded, and the sentences about pairing, deduplication, and pagination each carry distinct information. The middle sentence stacking dedup, excerpt, filter enforcement, and relevance score is slightly overpacked, but there is no filler.

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?

There is no output schema, so the description must explain returns, and it does: one document per filing, an excerpt, a separate relevance score, and an approximate total above 10,000. Combined with the pagination ceiling and the required date pairing, an agent has enough to call this correctly on the first attempt.

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 already 86%, so the baseline is 3, but the description adds meaning: it explains that offset pairs with nextOffset to continue and that pagination ends at 10,000, and restates the date-pairing constraint and form filtering as usage rules. It does not touch the limit parameter or clarify offset semantics beyond the schema, keeping it short of a 5.

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 first sentence gives a specific verb and resource ('Search SEC filing text') and states the scope choice (all filers vs. restricted to CIKs). It is unambiguous what the tool does, but it never names a sibling such as get_filing_section or list_recent_filings to draw the boundary explicitly.

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 gives real guidance on query construction ('unquoted words are ANDed', quoted phrases for exact matches, 'keyword search, not natural-language search') and on parameter pairing (dateFrom/dateTo together, forms for specific types). What it does not do is say when to reach for this tool instead of a sibling like get_filing_section or diff_filing_sections, so tool selection 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.