Spend Summary (what my agents spent and what was blocked)

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, and the description adds valuable context: it works offline against the local audit chain and clarifies that blocking occurs before execution. This goes beyond the annotation hints and enriches the behavioral understanding without contradiction.

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 concise and front-loaded: it states what the report contains, then adds read-only/offline context, and concludes with example questions. Every sentence contributes meaning, with no fluff or redundant phrasing.

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 a simple 1-param tool with no output schema, the description fully conveys what the report includes (payment decisions, paid amounts, recipients, blocked amounts, and mandate rules). It also provides example usage and notes offline capability. This is complete context for an AI agent to understand and correctly invoke the 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?

The only parameter 'days' is fully described in the schema (window in days, default 7, max 365), and the description's mention of 'time window' aligns but adds no additional technical detail. With 100% schema coverage, a baseline score of 3 is appropriate; the description doesn't need to compensate.

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 clearly states the tool's function: an operator report over a time window with specific metrics (number of payment decisions, amounts paid, recipients, blocked amounts, and mandate rules). This specific verb+resource+scope distinguishes it from siblings like list_decisions, which would provide detailed decisions rather than an aggregate summary. The example questions further reinforce its purpose.

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 provides clear context for when to use the tool ('Use this to answer questions like...'), with concrete example queries. However, it does not explicitly mention when not to use it or name alternative sibling tools, so it stops short of full when/when-not/alternatives guidance.

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