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

The description discloses critical behaviors beyond the annotations: the session_id format with a ?token= suffix and its necessity to avoid 401s, the instruction to never strip or paraphrase it, and the warning that Riley will ask questions the agent must forward rather than answer. It also notes the source parameter controls the 'Open {IDE}' button. These add substantial behavioral detail that annotations (openWorldHint: true, destructiveHint: false) do not convey.

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 longer than typical but each section serves a purpose: workflow label, session handling, usage trigger, and per-parameter guidance. It is structured with headers and bolded warnings, making it scannable. Minor redundancy exists (e.g., session_id importance repeated), but overall it is efficient for a complex tool.

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?

With no output schema, the description explains the expected response ('clean message from Riley' and 'session_id in the response metadata'). It covers the full context: initialization, user interaction, downstream tool requirements, parameter semantics, and even points to 'workflow.usage prompt' for further guidance. For a session-starting tool with 3 optional parameters, this is complete.

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 100%, so a baseline of 3 applies. The description enriches each parameter: project_context includes a detailed example and explicit exclusions (no credentials/PII), source includes auto-detection guidance and a list of accepted values, and github_username explains its pre-fill behavior. This goes beyond the schema's short descriptions, though the schema already handles basic meaning.

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 explicitly states 'WORKFLOW: Step 1 of 4 - Start infrastructure design conversation' and 'Open an InsideOut V2 session and receive the assistant's intro message.' This clearly identifies the verb (start/open), resource (infrastructure design conversation/session), and how it differs from siblings like convoreply or tfgenerate (it is the initial session setup step).

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 provides explicit when-to-use guidance: 'Use when the user mentions keywords like: 'setup my cloud infra', 'provision infrastructure', 'deploy infra', 'start insideout', 'use insideout', or similar intent to begin infra setup.' It also gives workflow context (step 1 of 4) and indirectly distinguishes it from alternatives by requiring the session_id for subsequent tools. However, it does not explicitly state when NOT to use this tool versus others, and relies on 'Examine workflow.usage prompt' for broader context.

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