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

Annotations already cover the read-only safety profile, but the description adds substantive behavioral context: research coordinators expose record_contract rather than completed results, codes are the only software a run may execute, and items absent from the catalog cannot run. These are non-obvious facts an agent could not infer from readOnlyHint. It does not describe response shape or size, which keeps it below 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 entire description is one enormous sentence with four nested parentheticals, several of which are themselves multi-clause sentences. The information is dense and relevant, but it is not front-loaded with a plain statement of what the tool is, and the nesting makes it hard to scan for the 'call before mcg_quote' rule buried at the end.

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 carries the full burden of explaining what comes back, and it does so in detail for all five sections, including the envelope needed for external_frontier and how recipe quote objects are consumed. An agent has enough to call the tool and act on the result; only the return format/size is unstated.

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?

The tool takes zero parameters, so per the baseline this scores 4. The description usefully spends its space describing the payload the agent will receive instead of parameters, which is the right trade for a no-arg discovery tool.

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 enumerates the five content groups the tool returns (simulation kinds, costed lineage menu, external-frontier graphs, recipes, codes) and implicitly establishes it as a catalog/discovery tool. It distinguishes itself from mcg_quote by stating it must be called first. It loses a point because no explicit verb ('list', 'returns') anchors the opening — the reader must infer from the noun phrase 'Enabled simulation kinds'.

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 before mcg_quote' is an explicit ordering instruction, and 'A kind or code absent here cannot run' states the consequence of skipping it, which is strong selection guidance. It does not name any sibling besides mcg_quote or state when-not to call it, so it stops short of the full when/when-not/alternatives bar.

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