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

Annotations already cover the safe-read profile (readOnly, idempotent, non-destructive, openWorld), and the description adds real behavior beyond them: delta row omission via `previous_revision`, retention of source clocks and diagnostics, null semantics for missing/withheld values, and the 100-row cap with next_offset pagination. The caveat that "unchanged is not proof of freshness" is a useful, non-obvious operational warning.

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?

Four short sentences, front-loaded with the core purpose and the delta mechanism, with no filler. "Retaining source clocks and diagnostics" is slightly jargon-heavy, but each sentence carries distinct information.

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?

With an output schema present, return values like next_offset and source clocks need not be re-explained, and the pagination/delta behavior is adequately covered. What is missing for a 7-parameter, 7-dataset query tool is any guidance on dataset selection, entity filtering, or date formats, leaving meaningful gaps for correct invocation.

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 0% across 7 parameters, so the description carries the burden and only partially discharges it: it explains `previous_revision` (delta semantics) and `limit` (100-row cap) and implies pagination via next_offset. The `dataset` enum values, `entity` semantics, and `start_date`/`end_date` formats are left entirely undocumented.

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 conveys that it returns compact source-cited research rows optimized for repeated agent calls, which is a recognizable resource, but the verb is implied rather than stated. It never distinguishes itself from the close sibling `financial_evidence_query`, so an agent cannot tell from the text alone which of the two to invoke.

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?

"for repeated agent calls" plus the instruction to pass the previous revision implies the polling/delta use case, which is genuine usage context. However, there is no explicit when-not or naming of an alternative such as `financial_evidence_query`, so the agent must infer the selection rule.

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