save_story

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

Annotations already declare a non-read-only, non-destructive, non-idempotent write, so the safety profile is carried structurally. The description adds genuine value beyond that: the concrete persistence target (stories: section or stories.yaml), the confirmation gate before saving, content-safety constraints (no internal system names, people, countries), and the return payload. It stops short of stating what happens on an overwrite or whether an existing story is replaced.

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 purpose is front-loaded in the first clause, which is good, but the single dense paragraph bundles destination, workflow, content policy and return value, with semicolon-chained instructions that are easy to lose. Nearly every sentence earns its place, yet the packaging is heavier than the payload requires.

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 usefully discloses what comes back (the story as saved, the file, and the story count). Combined with the storage location and the confirmation requirement, an agent has enough to call it correctly; only the overwrite/collision behavior for an existing story 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?

Schema coverage is 100%, so every parameter including id, did, hard, result, avoid and skills is already documented in the schema itself. The description's one added rule — only confirmed material goes in did/hard/result and the rest goes in avoid — is meaningful routing logic, but it largely restates what the avoid field description already says.

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?

States a specific verb and resource ('Add a story to the person's story file') and names the exact destination (the watchlist's stories: or stories.yaml beside it). It also scopes the content domain to drafted interview answers and mock interviews, which separates it cleanly from sibling tools like get_interview_prep and save_application_package.

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?

Gives an explicit trigger ('Use it after interviewing the person about one of get_interview_prep's story_gaps') and names the upstream sibling that produces the gap list. It also states the interaction protocol (one question at a time, label typical details as common patterns, confirm before saving), so when-to-use and how-to-use are both answered.

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