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

Annotations already cover the read-only, idempotent, non-destructive safety profile, so the bar is lower; the description still adds useful behavior beyond that: newest-first ordering, the auth requirement ('Any key role'), and the rich payload semantics. The interpretation of projected value ('NOMINAL horizon-end dollars against the current plan, not discounted, not realized') is genuinely valuable context, though pagination or result-size behavior is unaddressed.

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 dense but front-loaded sentences that lead with purpose before payload detail. The payload enumeration is long but earns its place because no output schema exists; nothing is clearly throwaway.

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?

With no output schema, the description carries the return-value burden and does so well by enumerating recommendation, intents, projected value, alternatives, caveats, and evidence. The main gap is pagination/volume behavior for a newest-first list, and the loose mapping of filters to parameter names.

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 only 25%, so the description should compensate more than it does. It restates the status enum (already in the schema) and gesturally mentions 'mandate or household' without tying those to mandate_id/household_id; api_key handling is covered only loosely by 'Any key role.'

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 ('Proposals Lodestar filed') plus scope ('for a person to decide, newest first') and the filter surface. It is distinguishable from get_decision/review_proposal by describing a browse-list of proposals, though it never explicitly contrasts itself with the sibling list_decisions.

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?

Implies usage through the optional filters and the note that 'Any key role' can call it, but never says when to reach for this versus list_decisions, review_proposal, or get_decision. No exclusions or routing guidance is given.

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