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

Annotations already cover readOnly/idempotent/closed-world, and the description adds substantial context beyond them: truncation of assignments at 2000, auth requirement (OAuth or API key), the fact that exports bypass MCP, and a prompt-injection warning that response texts and category names are data, not instructions. That last point is behaviorally important for an agent consuming untrusted text.

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 returned payload, then exports, then the optional assignments, then auth — a sensible ordering with no filler sentences. It is dense and close to a run-on, but each clause carries distinct information.

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, so the description must describe the return payload, and it does so thoroughly down to the level of the category tree fields and export formats. Auth, truncation, and the out-of-band download path complete the picture for a read-only three-parameter tool.

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%, and the description adds real meaning by tying include_assignments to a concrete truncation limit of 2000, which the schema does not state. hierarchy_id's 'defaults to newest' is repeated from the schema and project_id is left implicit, but it is self-evidently the project whose code frame is returned.

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 ('Returns the finished code frame of a project') and enumerates the contents: L1-L3 category tree, descriptions, examples, per-category response counts, summary counts, export URLs. This is clearly distinguishable from siblings like open_end_get_project or open_end_get_run.

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 word 'finished' implies this is called after a run completes, giving usable invocation context, and it explicitly routes export downloads away from MCP ('downloaded from the REST API with the same Bearer credential, not through MCP'). It stops short of naming which sibling to use for pre-run or in-progress state, so no explicit exclusions.

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