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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds the details annotations cannot: the delete is soft, data survives for compliance, the operation has a preview phase, and it can be rejected. That is meaningful behavior beyond the annotation set.

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?

Four tight sentences, front-loaded with what the tool does and its consequence, then the workflow, then the guardrail. No filler or repetition of the title.

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 mutation with no output schema, it covers reversibility, side effects, precondition, and the confirmation flow, which is nearly everything needed. The one missing piece is which of the two ID parameters to populate.

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 confirm and both ID fields are already documented and the baseline is 3. The description reinforces the confirm two-phase semantics but never clarifies the two mutually alternative identifiers (strategyId vs aiStrategyId) — with zero required params, the agent gets no guidance on which ID to supply.

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?

A specific verb+resource ("soft-deletes a strategy") plus the immediate consequence (gone from lists, unusable for backtests) and the assurance that data is retained. This clearly separates it from the many delete_* siblings (delete_file, delete_memory, delete_broker_credential) and from update_strategy.

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?

Explicitly prescribes the call sequence: without confirm/false to preview, confirm=true to execute. It also names a hard precondition and the remedy — "Refuses if the strategy has active deployments (stop them first)" — so an agent knows when not to call and what to do instead.

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