kb_refresh

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

Annotations already declare readOnlyHint=false and idempotentHint=true, so the write/idempotent profile is covered structurally; the description usefully adds the latency characteristic of a scan, which is not in the annotations. It stops short of saying what the rescan rebuilds, whether existing content is replaced or preserved, or whether concurrent searches block during the scan.

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?

Two sentences, the action first and the trigger condition second, with no filler. Every clause carries decision-relevant 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?

The existence of an output schema means return values need not be described, and the trigger/precondition is fully covered. However, for a tool exposing two undocumented optional parameters, the description leaves a real hole — the agent knows when to call it but not how to tune it.

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 0% — 'force' and 'evidence_limit' have titles and defaults but no meaning anywhere. The description never mentions either parameter, so an agent cannot tell what forcing a rescan changes or what an evidence limit controls, and must guess or omit them.

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 and resource ('Rescan the repository') and immediately distinguishes itself from the sibling kb_status by naming it as the gate for invocation. An agent can tell what this does and when it is the right tool without opening any 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?

'Only needed when kb_status reports the knowledge base as missing or stale' gives an explicit precondition and implies the when-not case (healthy knowledge base). It also supplies a cost caveat ('a scan of a large project takes a few seconds') that helps the agent decide whether to invoke now or defer.

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