firefly_destructive

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

The description goes well beyond the annotations: it warns that actions cannot be undone through the server, requires user confirmation, explains that record content must be treated as data rather than instructions, and describes response-size behavior. It also gives practical guidance on using the `fields` parameter to reduce large responses by ~90%. This adds substantial behavioral context beyond the raw annotations.

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?

The description is longer than a typical one-liner, but each section earns its place: purpose, entity/operation catalog, parameter lookup guidance, injection-safety warning, and performance tip. It is front-loaded with the core purpose and organized so an agent can quickly parse scope and safety requirements.

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-entity tool with no output schema, this description covers the critical areas: scope, undo risk, confirmation requirement, parameter discovery, prompt-injection hazards, and response-size management. It does not describe the normal return envelope, but the dry_run behavior is documented in the input schema and the agent is directed to firefly_get_schema for operation-level details, so the description is sufficiently complete for selection and safe invocation.

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 meaningful value by listing valid entity/operation combinations and giving a concrete `fields` example for summarising spending. It also clarifies that detailed operation parameters must be retrieved via firefly_get_schema, which helps the agent understand the relationship between `entity`, `operation`, and `params`.

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: 'Delete records, or rewrite one field across many records in a single call,' then enumerates the supported entities and operations. This clearly distinguishes it from the sibling tools firefly_query, firefly_mutate, firefly_list_operations, and firefly_get_schema, since it names destructive operations only.

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?

The description clearly frames when this tool is appropriate: destructive operations that cannot be undone, and it explicitly instructs 'confirm with the user first.' It also tells the agent to call firefly_get_schema(entity, operation) for operation-specific parameters. It does not explicitly contrast with firefly_mutate or firefly_query, but the destructive scope and entity/operation list make the intended usage clear.

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