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

Goes well beyond the annotations: discloses the return value (`personaId`), plan gating (Pro/Agency), and an extra permission requirement (`Personas` on top of Pro for QUALIFIER). Annotations only cover readOnly/destructive/idempotent flags, so this prerequisite and return contract information is genuinely additive.

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-loads the purpose and the blocking dependency in the first sentence, then the scope caveat and plan requirement. Slightly redundant — 'a QUALIFIER step needs one' and 'the flow save is rejected without it' convey nearly the same urgency — but nothing is wasted overall.

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 3-param create tool with a nested criteria object and no output schema, it covers the return contract, prerequisites, and plan limits. Minor gap: no mention of what happens when criteria are partially specified or whether the persona is immediately usable in flows.

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?

With 100% schema description coverage across all 3 parameters and rich per-field docs inside `criteria`, the schema carries the semantic load. The description adds no parameter-level guidance (e.g. whether `criteria` may be empty or how filters combine), so baseline 3 applies.

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 — 'Define an ideal customer profile' — plus the concrete artifact returned (`personaId`). It also carves out a hard boundary versus sequence tooling ('This defines the filter only; it does not add a QUALIFIER step'), but never explicitly contrasts with sibling persona_list / persona_update / persona_delete.

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 explicit ordering ('create the persona before calling `flow_set`') and the consequence of skipping it ('the flow save is rejected without it'). It also states what the tool is NOT for (does not add a QUALIFIER step to any sequence), which is exactly the when-not guidance an agent needs.

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