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

Annotations already cover safety (readOnly, idempotent, non-destructive), yet the description goes well beyond them: it discloses the `quality_caveat` field emitted for unscoped searches, the ±1 fiscal-year retry and its caveat, the latency/slowness delta for cross_company and the tens-of-milliseconds fetch mode, and the absence of ranking in fetch mode. This is exactly the behavioral context structured fields cannot carry.

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?

Long, but front-loaded with the core purpose and mode-selection rules before the parameter guidance, and nearly every sentence carries a distinct routing or behavioral instruction. There is mild redundancy between the description and the schema text for fetch mode and scope, which keeps it out of the top score.

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, so return-field documentation is unnecessary, and the description still flags the single return field worth checking (quality_caveat). Given 14 parameters, nested issuer object, 4 enums, and two operating modes, the description covers every decision an agent must make before calling.

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 86%, so the schema already documents most parameters and baseline would be 3. The description still adds real semantics on top: issuer must be a ticker (not cik) in this corpus, fiscal_year is independent of and layered over date_from/date_to, and order='earliest' is the correct pairing for onset questions. Only limit/profile escape mention.

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+resource (search earnings-call transcripts and press-release exhibits) and immediately scopes it by speaker turn, with concrete examples of what is covered. The closing contrasts it against financial_search ('pair with financial_search to back narrative with filed numbers'), so an agent can distinguish it from 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?

Explicit when-to-use (guidance, tone, forward-looking color filings lack), when-to-use-alternative (pair with financial_search), and an explicit warning that cross_company should be used deliberately only for genuinely multi-company questions. Fetch mode and onset/first-mention routing are each given their own selection condition, including the correct bound (date pair, not fiscal year).

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