create_session

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

With no annotations, the description carries the full burden, and it does disclose the key trait: local-only, no cloud session, no document switch. It omits lifecycle details an agent would want (does the session expire, is calling twice with the same fileKey idempotent, does passing sessionId re-attach to an existing session).

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 action and followed by the reuse rule and the disclaimers. 'Reuse it across calls, including explicitly selected other files' is slightly compressed and takes a second read, but nothing is wasted.

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?

A creation tool with no output schema and one undocumented required parameter. The description implies a UUID is returned and covers the local-vs-cloud scope well, but leaves the agent guessing about the purpose of 'description' and about session lifetime.

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 67%: fileKey and sessionId are documented in the schema, but the required 'description' parameter has no schema text and no explanation in the tool description either. The description adds no syntax or format meaning beyond the schema, so baseline 3 fits.

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 verb and resource ('Create a local task recording UUID') and immediately scopes it to 'the selected Figma file'. The final sentence distinguishes it from what an agent might otherwise assume (cloud session creation, document switching), which no sibling tool covers.

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?

'Reuse it across calls, including explicitly selected other files' tells the agent this is a per-task token rather than a per-call one, and the negative clause rules out two wrong intents. It stops short of naming an explicit alternative tool or a prerequisite sequence (e.g., call figma_status first), so not a 5.

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