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

Annotations already declare destructiveHint=true and non-idempotent, but the description goes further by disclosing the concrete destructive behavior ('reset archives the conversation and starts over') and the gating requirements (confirmation for AI usage, explicit user intent before reset). It does not describe return shape or intermediate session state, but for a mutation tool this is solid added context.

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 paragraph with the purpose front-loaded, followed by a compact semicolon-delimited action table, then the two constraints. No sentence is filler; every clause conveys either an action's semantics or a prerequisite.

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 destructive, multi-action, no-output-schema tool this covers the essential dispatch semantics, gating, and scope limits. The remaining gap is that brandId is unexplained and session lifecycle/state is only loosely implied, but an agent has enough to invoke 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 only 25%, so the description must compensate, and it does for the critical discriminator: it defines the behavior of all six action enum values, which the schema lists bare. The confirm parameter's meaning is reinforced ('confirmation for AI usage'), but 'answer' and especially 'brandId' receive no explanation in either place.

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 ('Run Dalea's strategy interview') and then decomposes the tool into its six named actions, so an agent understands exactly what capability this is. It is clearly distinguishable from sibling readers like get_strategy_interview and update_strategy_brief.

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?

Maps each action value to its intent (start resumes, answer advances, append refines, reset archives+restarts, apply activates complete, apply_partial activates usable partial), which is precisely the routing guidance needed for a multi-action tool. It also states prerequisites (confirmation for AI usage, explicit user intent before reset) and a scope exclusion ('Does not apply suggested restrictions'), though it never names a sibling alternative to prefer in any scenario.

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