set_narrative

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

With no annotations supplied, the description carries the whole burden, and it does disclose meaningful side effects: it writes summary.md and regenerates REPORT.html and REPORT.md using the original run's options. It stops short of stating whether an existing narrative is overwritten, what happens if the report directory is missing, or whether errors are raised, which are the details an agent needs before a mutating call.

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?

Two tight sentences, with the primary action and placement front-loaded and the side effects following. No filler or repetition, though the embedded line break slightly interrupts the read.

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 two-parameter mutation tool with no annotations and no output schema, the description covers purpose, the upstream narrative_prompt dependency, and the files emitted. It is still missing report_dir semantics, overwrite behavior for an existing summary, and any indication of the return value, so an agent could call it correctly but not predict all outcomes.

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 description coverage is 0%, so both parameters depend on the description. The text parameter gains real meaning (the narrative written from narrative_prompt), but report_dir is never mentioned in the description at all, leaving half the parameters undocumented in both structured and unstructured form.

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 verb and effect (embed a narrative summary at the top of the report) plus the concrete artifacts produced (summary.md, regenerated REPORT.html/REPORT.md). It also distinguishes itself from the sibling narrative_prompt by naming it as the source of the text, so an agent can tell generation-of-prompt from insertion-of-text.

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?

Usage is implied through the workflow dependency on narrative_prompt ("yours, written from narrative_prompt"), which tells the agent this follows a prompt-generation step. However, there is no explicit when-to-use/when-not guidance, no stated prerequisites such as an existing report or run directory, and no mention of what to do if no report exists.

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