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

Annotations already declare readOnlyHint=false and idempotentHint=false, and the description adds genuinely non-obvious behaviour on top: "Returns duplicates to confirm instead of copying" explains how the non-idempotent write is guarded, and the privacy rule ("No names, contacts or your person's private data") is a real constraint not expressible in schema. It stops short of a 5 because it says nothing about validation failures, auth requirements, or what happens when a contribution is rejected or merged.

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?

Front-loaded with the one-line purpose, then structured per-parameter, with almost no filler words. The inline JSON-ish notation is dense and slightly harder to parse than prose, but it packs a large amount of contract information into a short block.

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 need not be explained, and the duplicate-return behaviour is still flagged anyway. But for a mutation tool with 8 parameters, two required-parameter semantics (kind's allowed values, region's meaning) are missing, and the description gives no indication of failure modes or what an agent should do after a duplicate is returned for confirmation.

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?

With 0% schema description coverage across 8 params and nested objects, the description carries the full burden and does so well: it enumerates the four subject shapes, the five evidence type values with observed_at/url, the payload pointer, the text_en length/format rule, and the text_original+lang condition. The gaps are `kind` (required, the central discriminator, referred out to hirelog_kinds) and `region`, which is never mentioned at all.

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?

"Add one typed fact" names a specific verb plus a specific resource, and the typed-subject enumeration makes clear what a 'fact' is. It is distinguishable from siblings because it explicitly defers field definitions to hirelog_kinds rather than duplicating search/company/market behaviour. It does not explicitly contrast itself with hirelog_vote or hirelog_check_posting, so it stops short of a 5.

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?

There is implicit routing ("see hirelog_kinds" for payload fields, "add text_original + lang if observed in another language"), which tells the agent prerequisites for correct use. However, there is no explicit statement of when to use this tool versus hirelog_search/hirelog_vote, and no statement of when not to contribute. Usage is largely inferred from the parameter contract rather than stated.

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