ps_corpus_import

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

With no annotations, the description carries the full behavioral burden and does add real context: crowd text cannot become evidence because each item declares its own authored tiers, and dry_run stores nothing. It omits idempotency/overwrite behavior on the target corpus and permission requirements for a write operation.

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 sentence, followed by the tiering guarantee and dry_run note. Structurally efficient, with only the README redirect detracting slightly from self-containment.

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 return values needn't be explained, but the payload is a nested free-form object the description defers to src/mcp/README.md, and two path parameters are unexplained. For a tool with nested input and tiering logic, that redirect leaves gaps.

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 0% across 5 params, so the description must compensate. It explains payload shape ({"items": [...]}) and dry_run semantics, and references `sections` for tiering, but config_path, periscope_path, and the tiering parameter itself are left undocumented in both schema and description.

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 uses a specific verb+resource ("Import a user export ... into the evidence corpus") and clarifies the intent versus scraping-based sources. It implicitly distinguishes itself from the read-oriented siblings like ps_corpus_search, though it never names an alternative tool explicitly.

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 a concrete when-to-use rule: "Use this for sources Periscope must not scrape," and describes the dry_run preview path as the safe way to test acceptance. No explicit when-not or named-alternative routing is provided, so it stops 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.