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

With no annotations, the description carries the full behavioral burden and does so well: it discloses that execution is asynchronous ('Returns immediately'), that explicit graph membership (owner or member row) is required, that cost is bounded by the caller's monthly spend cap on that graph, and that the saved snapshot (not the draft) is what executes. These are exactly the non-obvious traits an agent needs before firing a launch.

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?

Three tight sentences, front-loaded with the action and followed by behavioral constraints in order of importance (mode, sync/async, permission, cost). Every clause carries information; nothing is repetitive or padding.

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?

There is no output schema, and the description compensates by stating what the call returns behaviorally ('returns immediately') and how to obtain results ('poll get_run for status'). Combined with the disclosed permission and spend constraints, an agent has everything needed to invoke and follow through correctly.

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 schema already documents graphId, input, and context, giving a baseline of 3. The description adds no per-parameter detail (no format hints, no interplay between input and context) beyond what the schema states.

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?

Opens with a specific verb+resource pair ('Launch a run on a graph') and immediately narrows scope with 'pinned mode (the saved snapshot)' and 'attributed to the caller.' This cleanly separates it from siblings like create_graph, resume_run, and get_run without the agent needing to open any schema.

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?

It gives clear usage context by naming get_run as the required follow-up for status, which routes the agent correctly after the call. It does not, however, contrast itself with alternatives such as resume_run (restarting a paused run) or cancel_run, so the when-not-to-use case is left to inference.

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