Deploy Graph

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

With no annotations, the description does real work: it discloses the default start behavior, that replace_previous stops AND deletes the previously deployed session (a destructive side effect), and that a failed start deletes the new session and surfaces the runtime error. Missing only auth/permission requirements and whether the call is idempotent.

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 short sentences, front-loaded with the primary behavior and followed by the two conditional/side-effect clauses. No filler, no repetition 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 two-boolean-parameter deployment tool with an output schema, the description covers defaults, the destructive replace behavior, and failure cleanup. Only preconditions (auth, graph validity requirements) are left unstated.

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 coverage is 0%, so the description must compensate, and it largely does: replace_previous is explained in terms of exactly what it stops and deletes, and 'by default' conveys start=true. It does not explicitly describe start=false (create without starting), leaving that one inference to the reader.

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 names specific operations (validate, create a backend session, start it) on a specific resource (the graph), which clearly separates it from siblings like validate_graph, save_graph or control_session. The multi-step nature is stated up front, though it does not explicitly say how it differs from chaining validate_graph + new session.

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?

Usage is implied by the operation sequence: this is the 'make it live' step, and replace_previous=default-true signals redeploy semantics. However, no alternative is named — nothing says to use validate_graph for a dry run, control_session to start/stop an existing session, or how to choose replace_previous=false.

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