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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely new state behavior: the widget reuses captured source numbers and selection, and expired evidence requires an explicit new read — a failure mode the annotations do not express. It stops short of describing any rendering error path beyond expiry.

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, then prerequisite, then misuse boundary, then lifecycle caveat — a sensible order with no filler. The negation list and the expiry sentence are both doing work, though the prose is denser than strictly necessary.

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 need no explanation; what remains — prerequisite, decide-when-to-use rule, anti-patterns, and stale-evidence handling — is all stated. Nothing an agent needs to invoke this single-parameter widget correctly is missing.

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% (pattern, provenance, 'do not supply chart numbers' are all in the schema), so the baseline is 3. The description earns above that by tying the argument's provenance to research_discover and explaining the server-side reuse of original values, which clarifies why the agent cannot fabricate the id.

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 ('Display a focused asset directory widget') and immediately scopes it as a visual companion to research_discover output rather than a data source. This distinguishes it cleanly from data-fetch siblings like research_read_evidence and from the other research_show_* widgets.

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 gating conditions: evidence must already exist from research_discover, and 'Use only when a visual helps answer the question.' It also names four things it is not (data fetch, calculation, navigation hub, replacement for interpretation), which is exactly the alternative-routing an agent needs to avoid substituting it for a computation tool.

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