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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely useful behavior beyond that: it is presentation-only, reuses captured source numbers and selection rather than re-fetching, and becomes stale once evidence expires, requiring a new read. It does not describe rendering failure modes, but the output schema covers the return shape.

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 with no filler: purpose first, then usage constraints, then staleness behavior. The negation list ('not a data fetch, calculation, navigation hub...') is dense but each item earns its place by ruling out a plausible misuse. Slightly overpacked, but well structured.

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, full annotation coverage, and a single fully described parameter, the description covers everything an agent needs to select and invoke the tool correctly, including the prerequisite evidence and the expired-evidence case. The only small gap is what the widget contains beyond direction labels, which is minor against the output schema.

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% and the evidence_id description already explains the hash format and that the server retrieves original values and selection. The description adds only that it 'Reuses captured source numbers and selection', which reinforces but does not extend the schema's parameter contract. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

Opens with a specific verb and resource ('Display a focused liquidation chart widget') and scopes the content ('Long and short liquidation flows over the selected period, with separate direction labels'). It also distinguishes itself from the data layer by tying itself to prior evidence from research_read_series, so an agent can separate it from sibling show_* tools without reading schemas.

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?

Explicitly states when to use it ('Use only when a visual helps answer the question') and when not to ('Not a data fetch, calculation, navigation hub or replacement for the assistant's interpretation'), and names the alternative path ('expired evidence requires an explicit new read'). That is a complete routing rule, not an implied one.

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