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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, and the "Read-only" line is consistent with them. Beyond that, the description adds genuinely behavioral context the annotations cannot: the 24-hour default window when `since` is omitted, and the output-usage constraint that every figure carries a qualification and must be reported as given rather than derived. It does not cover permissions or scoping to the caller's company, which keeps it at 4.

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 payload contents are front-loaded in a single dense sentence, followed by the reporting caveat and a short read-only tag. Every clause carries information, though the enumeration of returned categories is long and could be trimmed given an output schema exists.

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-shape detail is not strictly required, yet the description usefully previews the categories an agent will receive. The main gap is that it never states which company scope the briefing is drawn from or whether the caller must own the raise tied to companyId. For a read-only tool with a full output schema, that is a minor omission.

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 50% schema coverage the description must compensate, and it does for `since`: it defines the parameter's meaning and, critically, its default of the last 24 hours, which the schema does not state. The `companyId` object-wrapped UUID is left unexplained in both schema and description, so compensation is partial rather than complete.

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 verb ("Returns") and resource ("briefing inputs") are explicit, and the description enumerates exactly what the payload contains: touches, proposals, aging relationships, upcoming meetings, stage counts. That content list effectively separates it from analytics-style siblings like fundraising_get_fundraising_analytics or fundraising_get_channel_ledger. It stops short of naming any sibling as an alternative, so it lands at 4 rather than 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?

Usage is implied by the framing: the default 24-hour window signals a routine daily-briefing call. There is no explicit "use this when..." or exclusion against the many other fundraising read tools (get_insider_brief, get_list_due_follow_ups, get_fundraising_analytics), so the agent must infer the routing.

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