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

Annotations already declare a safe, idempotent, closed read, so the description correctly spends its words elsewhere: it reuses captured values and selection rather than recalculating, and it discloses the evidence-expiry behavior that forces a re-read. It does not describe what the widget returns, but the output schema covers that.

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?

Front-loaded with the action and data scope, with prerequisites and exclusions after. The run of negatives ('not a data fetch, calculation, navigation hub...') is slightly listy but each clause forestalls a real misrouting.

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?

For a one-parameter, annotated, output-schema-backed widget, the description supplies everything an agent needs: the dependency on a prior read, the visual-only trigger, the reused-selection behavior, and the expiry rule.

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 evidence_id's origin and 64-hex format are already documented; the description still adds real meaning by tying it to a prior research_read_series call, stating that captured numbers and selection are reused server-side, and flagging that evidence can expire.

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 concrete verb and resource ('Display a focused open interest chart widget') and pins the content precisely ('USD open interest by reported venue', separate lines, not an invented aggregate), which separates it from a data-fetch sibling. It does not name a specific alternative show_* tool, but the open-interest scope is unmistakable.

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?

Gives an explicit prerequisite ('after evidence from research_read_series is available'), an explicit use condition ('Use only when a visual helps answer the question'), and explicit exclusions ('not a data fetch, calculation, navigation hub'). It also covers the stale case: 'expired evidence requires an explicit new read.'

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