umlforge_suggest

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds genuine context beyond that: it discloses the response contract (tool name, pre-filled parameters, one-line explanation, plus a suggested alternative). It doesn't note the non-idempotent behavior, but that is carried by the 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?

Front-loaded with a 'START HERE' banner and a numbered outcome list, then use-case bullets, examples, and arg guidance — well organized and scannable. There is mild redundancy across the numbered list, the USE THIS WHEN block, and the example inputs, but each section serves a distinct purpose so nothing is pure filler.

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 single-parameter router with an output schema and full annotation coverage, this is complete: an agent knows what it does, when to invoke it, how to phrase the argument, and what the response contains. No relevant invocation detail is missing.

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 0% and the input schema gives only a bare string type, so the description must carry the full burden — and it does. It explains that task_description should contain URLs, entity names, service names, and tech stack, and reinforces this with four concrete example inputs, teaching the agent exactly how to populate the single required parameter.

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 function: given a plain-English goal, identify the right tool, return the exact pre-filled tool call, and explain the choice with an alternative. This clearly distinguishes it from its 14 siblings as the meta-router/dispatcher. An agent immediately knows this is the entry point rather than a domain tool.

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 'USE THIS WHEN' block gives explicit conditions: unsure which tool, wanting a ready-to-run recommendation from a goal, avoiding trial and error. Strong positive guidance, but it never states the inverse (skip this and call the specific tool directly once you know it), so it stops short of full when/when-not coverage.

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