narrative_prompt

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

With no annotations, the description carries the burden alone. It discloses the key behavioral contract — the tool returns instruction text that must be followed verbatim and whose output is consumed by set_narrative — which implies a read-only, non-destructive role. However, it never states that nothing is written or committed, and it says nothing about whether the prompt varies by report context.

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 short sentences, zero filler, and the next-step instruction is front-loaded where an agent will act on it. The opening noun fragment is slightly less scannable than a verb-led sentence, but nothing is redundant.

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?

An output schema exists, so the returned prompt's shape need not be explained, and the handoff to set_narrative is covered. What remains unexplained is the role of report_dir (whether omitting it targets a default report) and whether the prompt depends on prior analysis steps, which matters for an agent sequencing this workflow.

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% for the single optional parameter report_dir, and the description never mentions it, so there is no added meaning beyond the name. The name is reasonably self-explanatory and there is only one optional parameter, which limits the damage, but the description does not compensate for the coverage gap.

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 identifies a specific resource (the narrative-writing prompt) and its place in the report (top-of-report plain-language summary), which distinguishes it from siblings like section, summary, and analyze. It reads as a noun phrase rather than an explicit verb ('returns the prompt for...'), but an agent can still tell what it yields and where the output goes.

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 an explicit workflow: fetch this prompt, follow it exactly, then hand the resulting text to set_narrative. That is clear when-to-use and what-to-do-next guidance. It doesn't state exclusions or when another sibling (e.g. summary, section) would be the better choice, which keeps it short of a 5.

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