flowforge_manage_pronunciations

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely new behavioral information: a 'delete' without confirm=true only performs a dry run, which tells the agent that the first delete attempt is non-destructive and must be repeated to take effect. It does not disclose the duplicate-entry conflict behavior (that detail lives in the schema), so it stops short of a 5.

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?

One action sentence followed by a short 'Returns' note; the scope and the dry-run caveat are front-loaded and every sentence carries information. No filler, no restating of the tool name.

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 CRUD tool, the definition covers purpose, the action set, and the key safety nuance, and an output schema exists so return-value detail is unnecessary. The only meaningful omission is a note on the duplicate-entry conflict and on which fields are mandatory for create/update, both of which the agent must discover in the schema rather than the description.

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?

The description itself names no parameters and does not explain assistant_id, pronunciation_id, fields or response_format. It does add meaning for 'confirm' by linking it to dry-run behavior for delete, which goes beyond the schema's terse 'Required true for delete'. The nested schema properties are in fact well documented, so the marginal gap is tolerable, but the description does little of the semantic work.

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 gives explicit verbs (list, create, update, delete) tied to a concrete resource (an assistant's pronunciation entries) and even defines the domain concept in a parenthetical ('how TTS should say a written word - brand names, acronyms, surnames'). No sibling tool touches pronunciation dictionaries, so there is no ambiguity to resolve, and an agent knows exactly what this tool operates on.

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 four supported actions are named, which implies the usage mode (CRUD on one assistant's dictionary via the 'action' parameter), but the description never states when to reach for this tool versus alternatives such as flowforge_api_request or flowforge_update_assistant, nor does it give any per-action preconditions. Usage is inferable rather than guided.

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