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

Annotations already declare readOnlyHint, openWorldHint, and destructiveHint. Beyond those, the description usefully discloses the return contents and that amounts are denominated in the plan's currency, which is real behavioral context. It does not mention pagination or result size, keeping it short of a 5.

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?

One tight sentence plus a short currency note, with the resource and returned data front-loaded and no filler. Every clause earns its place.

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's enumeration of returned values is genuinely valuable, and annotations carry the safety profile. Missing only secondary details such as result volume or how settlement suggestions are computed.

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 100% and the single 'plan' parameter is thoroughly documented in the schema (link format, 4-char id, draft-link caveat). The description adds nothing about the parameter, so the baseline 3 applies.

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 description gives a specific verb and resource ('Read the plan's shared costs') and enumerates exactly what is returned (expenses, balances, settlement payments). It implicitly separates itself from the mutating siblings add_expense and record_payment, but never names an adjacent read tool such as get_plan, so differentiation is inferred rather than stated.

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 no guidance on when to prefer this tool over get_plan or other read siblings, no prerequisites, and no stated exclusions. Usage is only implied by the phrase 'the plan's shared costs'.

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