invariance_narrative_get

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

The description discloses a non-trivial behavioral trait: this tool can 'regenerate' the narrative, not just fetch it, which is reinforced by the schema's 'Force regeneration' parameter. This adds context beyond the readOnlyHint and openWorldHint annotations, warning the agent that refresh may trigger an LLM synthesis. It does not contradict the readOnlyHint outright, though 'regenerate' could be misread as mutating, which is worth noting.

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 a single, front-loaded sentence with no filler. 'Fetch (or regenerate)' efficiently captures both primary and secondary behaviors, and 'LLM-synthesized narrative for a run' precisely scopes the resource. Every word earns its place.

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 simple getter with a small schema and read-only annotations, the description and schema together are sufficient to invoke the tool correctly: pass run_id and optionally set refresh. The absence of an output schema is mitigated by the clear 'narrative' concept, though the exact return shape is not described. Overall, no critical information for calling this tool is missing.

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 input schema already documents the refresh parameter clearly, and the required run_id is self-evident from the name and description. The description does not add much parameter-specific meaning beyond the schema, but the schema covers half of the parameters and the other half is obvious. A middle score is appropriate because no additional compensation is needed.

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 clearly identifies the verb ('Fetch') and the resource ('the LLM-synthesized narrative for a run'), going beyond the tool name. The parenthetical '(or regenerate)' adds an important secondary behavior. It does not explicitly differentiate itself from siblings like invariance_run_get, but the unique 'narrative' and 'LLM-synthesized' terms make the target resource specific enough.

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 description implies when to use this tool: whenever the agent needs the synthesized narrative for a run, and potentially wants to regenerate it via the refresh behavior. However, it does not explicitly state when to prefer this over related run tools, and there are no alternatives or exclusions mentioned. The usage context is implied rather than stated.

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