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

Annotations carry only a title, so the description bears the full behavioral burden and does add real context: the data is live and 'will change', the answer must be timestamped, and it must never be persisted as a memory. It stops short of disclosing permissions/auth requirements or whether running a remote tool can mutate external records — a meaningful omission for a dispatcher that can execute arbitrary downstream tools.

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?

Purpose and the recall-vs-system rule are front-loaded, and the mode mechanics follow in order of increasing specificity. It is dense with semicolon-chained clauses and runs longer than strictly necessary, but no sentence is filler.

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 4-param dispatcher with a nested `arguments` object, no output schema and no behavioral annotations, the description covers invocation modes, data volatility, and the record-identification workflow well. It leaves gaps on error/unknown-system behavior and on whether executed tools can be destructive, which the missing annotations would otherwise need to cover.

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 description coverage is 100%, so the baseline is 3, but the description adds interaction semantics the schema does not: the unset/system/system+tool progression maps the parameters to distinguishable behaviors and outcomes. It also warns that a child agent must wake separately for `kit_session_id`, adding intent beyond the field's own note.

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?

The description states a specific verb and resource — asking connected business systems (accounting, HR, shop) for live records — and explicitly distinguishes itself from the sibling `recall` ('Kit's memories hold the history... a system holds today's records'). It also spells out the three progressive modes (list, inspect, run), so an agent knows exactly what class of tool this is without opening the schema.

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 an explicit routing rule against alternatives: for a customer/person/order question, 'recall first, then ask the system for the current figures', with recall naming the record to ask for. When-tos are also encoded in the mode contract ('with nothing it lists... with system, a tool's arguments... with system and tool, it runs that tool'), leaving little to inference.

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