design_session_start

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

There are no annotations, so the description carries the full burden, and it does well: it discloses that the journal is append-only and survives context compaction, client restarts, and model switches, which is exactly the kind of non-obvious persistence semantics an agent needs. Gaps remain on side effects (does it write a file on disk, is it idempotent, does an existing id overwrite state) and on failure modes.

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 the verb and the durable-journal rationale, then lifecycle guidance, then Args/Returns. Slightly redundant: the Args and Returns blocks restate what the schema and the existing output schema already declare, but they are short enough to earn limited blame.

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-parameter session-initialization tool with no annotations, the description covers purpose, lifecycle placement, persistence guarantees, and follow-up siblings; an output schema exists so the return-shape note is a bonus rather than a need. The one thing an agent still cannot infer is behavior on session-id collision or reuse.

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 documents both parameters: `requirement` as the design requirement text and `session_id` as an optional explicit id defaulting to a timestamp. That fully closes the coverage gap, though it adds no format or length constraints beyond what the type already implies.

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?

Specific verb+resource ("Open a durable design-session journal for an autonomous run") plus a stated scope ("spec-to-board task"). It also implicitly distinguishes itself from its siblings design_session_log ("log stage results") and design_session_resume ("read ... to know what's next"), so an agent can tell it apart without opening 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?

"Call this once at the start of a spec-to-board task, then log stage results as you go and read `design_session_resume` to know what's next" gives clear when-to-use and routes to the right follow-up tools. What is missing is the negative case: what to do if a session already exists (resume instead of start?) or what happens if a duplicate session_id is supplied.

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