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

Annotations already cover read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds meaningful context beyond them: it names the return shape (gifts[], modeled_portfolio_impact) and discloses the provenance guarantee ('verified claims only — never invents CE') plus the caveat 'modeled≠guaranteed'.

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?

Two tight sentences, front-loaded with the verb and resource, then the return contract. Some compression is excessive ('never invents CE' is internal jargon an uninitiated agent may not resolve), but nothing is wasted.

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?

Given 9 parameters, low schema coverage, and no output schema, the description does supply the key output field names and a provenance caveat. However it leaves the effect of risk, tax, geography, include_funds and top_n unexplained, which is a real gap for an allocation tool.

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 description coverage is only 33%, so the description must compensate, and it does not. It explains budget_usd and the method enum, but says nothing about tax, risk, geography, top_n, include_funds, or red_lines — all of which materially change the allocation an agent gets back.

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 ('Suggest a donor portfolio: split budget_usd across top-ranked orgs') and enumerates the three allocation methods. It is clearly a multi-org allocation tool, distinguishable in spirit from single-org siblings like recommend_charity, though it never names those siblings 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?

Usage is implied: this is the tool for splitting a budget across multiple orgs by method. But there is no explicit 'use this when X, use recommend_charity/compare_charities when Y', and no stated prerequisites (e.g. whether orgs must already be ranked, whether budget must exceed a minimum).

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