fusion_recompute

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does reveal one key trait: it will not fabricate replacements for broken references, which implies it only reports issues rather than auto-fixing them. However, it does not state whether the operation modifies the design, requires specific permissions, or what the response format is, leaving important side effects unaddressed.

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 a single, compact sentence that conveys the core action and a key limitation. It is front-loaded with the primary purpose and adds the caveat at the end, with no wasted words. This is appropriately concise for the amount of information it carries.

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?

The description is incomplete for an agent to call the tool correctly. It lacks an explanation of the parameters, any mention of prerequisites (e.g., an active document), and details about the output format beyond 'report remaining problems'. Given there is no output schema and no annotations, the description should cover these but does not, leaving significant ambiguity.

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 schema defines two required parameters (document_id and operation_id) with zero description coverage, and the tool description does not mention them at all. The agent has no clue what these parameters represent or how they relate to the recompute operation, forcing it to guess from names alone. This is a critical failure for a tool with no schema descriptions.

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 clearly states the action ('Recompute the design') and the expected outcome ('report remaining problems'), and adds a specific behavioral distinction: it does not invent replacements for broken references. This differentiates it from siblings like fusion_validate_design or fusion_check_interference, making its purpose unambiguous.

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 gives no guidance on when to use this tool versus alternatives. It does not mention any conditions, prerequisites, or mention of other tools, leaving the agent to infer usage context solely from the name and general description. This is a significant gap given the large sibling set.

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