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

With no annotations provided, the description carries the full behavioral burden and does so well. It declares the operation read-only, explains that null means no limit, notes conservative defaults for new agents, and describes typed error codes with remaining-cap details when limits block a spend.

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 description is front-loaded with the core action and then packs limit categories, null semantics, defaults, error codes, and key requirements into a compact set of sentences. No sentence is redundant for an agent deciding how to call the tool.

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 one-parameter read tool with no output schema, the description is complete enough to call correctly and interpret the result. It covers scope, null semantics, defaults, relevant error names, and authentication behavior.

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?

The single parameter is fully covered by the schema as 'Operator key only', and the description adds useful context by explaining that agent keys read their own policy while operator keys pass agent_id. This is meaningful beyond the schema despite the high coverage baseline.

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 states a specific verb and resource: reading spend limits on an agent. It enumerates the limit categories and makes clear this is a read-only policy inspection, which implicitly separates it from the mutation sibling set_spend_policy. However, it does not explicitly distinguish itself from other adjacent read tools such as get_budget_status.

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?

The description gives clear usage conditions for authentication: an agent key reads its own policy, while an operator key must pass agent_id. It also frames the result as useful when understanding limits or blocked spends. It lacks explicit guidance on when to choose this tool over a related sibling like get_budget_status.

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