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

Adds substantial context beyond the sparse annotations (openWorldHint=false, destructiveHint=false): signals are refused without a resolvable source URL and publication date, signals for unwatched subjects are silently dropped, and observedAt/screening verdict are platform-set rather than caller-supplied. It also reassures that no stage, tier, or plan value changes. It does not address idempotency or what happens on partial rejections, which is the remaining gap for a write tool.

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?

Four tight sentences with no filler, front-loaded with the core purpose before the validation constraints. Dense but every clause carries a distinct rule; slightly long compound sentences are the only cost.

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 five-parameter nested write tool with an output schema present, the description covers the conceptual model, the admission rules, and the side-effect boundaries an agent needs to call it correctly. Remaining gaps (startedAt, instructionFlagged, kind values) are narrow enough that an agent could still act, but not negligible.

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 only 20% schema description coverage, the description does useful work: it maps the three arrays (signals, quiet, unreachable) to their meaning and pins down that sourceUrl and publishedAt are mandatory. However, it says nothing about startedAt, companyId, the kind enum, or instructionFlagged, leaving several nested parameters undocumented in both places.

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?

Opens with a specific verb+resource ('Record one sweep of public sources') and immediately enumerates the three buckets the call carries: published signals, quiet subjects, and unreadable subjects. This is clearly distinct from read-side siblings such as fundraising_list_outside_signals or fundraising_list_watch_subjects. It stops short of naming an alternative, which keeps it out of the top band.

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 by the framing of a completed sweep and by 'it is evidence a proposal can then cite', which hints at the downstream proposal workflow. There is no explicit when-to-call or when-not-to-call statement and no named alternative for the read paths (listing signals or watch subjects). Adequate but leaves routing to inference.

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