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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so safety is covered; the description reinforces with "Read-only, no browser" and adds genuinely new behavior: newest-first ordering, offset paging, and the total/truncated signals plus the changedSinceDecision "as of the last tray read" caveat.

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?

A single dense, front-loaded paragraph that leads with what the tool reads, then filters, then ordering/paging. No filler sentences; every clause carries 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 10 optional parameters and no output schema, the definition covers filtering, default account scope, ordering, pagination, and the total/truncated return signals, so an agent has everything needed to call and interpret it correctly.

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 adds real meaning: decision=wrong_lane surfaces routeTo, changedSinceDecision tracks headline/company drift since judgment, and omitting the account widens to every visible account. These go beyond the schema's per-parameter text.

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?

"Read the triage memory" states a specific verb and resource and immediately enumerates its scope: who was judged, what was decided, and why. It is clearly distinguishable from the write-side sibling li_import_invitation_decisions and from generic listing tools.

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?

It gives concrete use cases (monthly rejection reporting, auditing routing via decision=wrong_lane) so an agent knows when to reach for it. It does not explicitly name an alternative tool or state when-not to use it, which holds it below a 5.

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