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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior: timestamps reflect FXMacroData storage time, earlier untracked revisions and publisher publication times are unavailable, and no API key is needed. That is real disclosure beyond the structured fields, though retention window length is still unstated.

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?

Three front-loaded sentences: purpose first, pagination mechanics second, caveats and access last. Dense and largely waste-free, though the middle sentence is long enough that the pagination instruction could be split for faster scanning.

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-value shape need not be described, and the description covers data provenance limits, access requirements, and cursor mechanics. The one gap is the absence of any tie-in to the sibling 'risk_sentiment' tool, which matters for an agent choosing between a snapshot and a change feed.

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 baseline is 3, but the description goes beyond the schema by explaining the output-to-input coupling: the next page's after_sequence should come from pagination.next_after_sequence. That tells the agent how to drive the cursor, which the per-parameter schema text alone does not.

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 (poll) and resource (retained risk-sentiment changes), and enumerates the change kinds it covers: additions, score revisions, and input-metadata changes. It does not, however, distinguish itself from the sibling 'risk_sentiment' tool, so an agent must infer the relationship between the current-state tool and this change-feed tool.

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 concrete invocation guidance ('pass pagination.next_after_sequence as after_sequence on the next page or poll'), which is useful, and notes access terms (free, no API key). But it never states when to prefer this tool over 'risk_sentiment' or when this feed is the wrong choice, leaving usage implied rather than explicit.

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