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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered and the description does not contradict it. The description adds real behavioral context beyond the annotations: what is returned (a short Python runner), that nothing needs installing, and the no-Python fallback. It omits execution/return-format details of the runner itself, so not a 5.

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 front-loaded with the primary trigger and the primary outcome, then adds the fallback instruction. Sentences are dense but each carries information; the 'Ask the user for their real data, run the agent, and show the result' sentence is slightly prescriptive/duplicative but still actionable.

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 one optional parameter, full schema coverage, no output schema, and annotations covering the safety profile, the description covers what an agent needs: when to invoke, what it returns, and what to do without Python. Naming the sibling check_agent as the upstream step closes the main routing gap; only the exact usage of the returned runner is left implicit.

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?

There is only one parameter (filename) and schema description coverage is 100%, so the schema already documents its meaning and expected format ('invoice_triage_agent.py'). The description adds no further semantics about the filename (e.g. where it comes from or whether it must match the checked agent), so the baseline of 3 applies.

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 states a specific outcome: it 'Returns a short Python runner so you can run the agent in this chat with your own Python tool on the user's own data.' This clearly distinguishes it from siblings like check_agent and get_agent_code by naming the concrete artifact returned. It stops short of a 5 because the verb ('use') is generic and the differentiation from get_agent_code/how_to_run_agent is only implied.

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?

It gives explicit triggering conditions ('right after an agent passes check_agent, or whenever the user wants to try an agent') and names check_agent as the upstream step. It also supplies a fallback path ('If Python is unavailable, apply the agent's logic yourself'). No explicit 'do not use this when...' exclusion against other siblings, 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.