midaz-execute

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

Annotations already indicate destructive=true, readOnly=false, and idempotent=false. The description adds no further behavioral context—no mention of authentication, rate limits, error handling, or what happens on mutation (e.g., requiring confirmation). The only extra info about mutations appears in the schema (mutationReason, confirmMutation), not the description. Thus, the description adds minimal value beyond annotations.

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 concise sentences, front-loaded with the core action ('Execute Midaz API operations'). It efficiently states the primary workflow (discover first) and scope without fluff. Could be slightly improved by including a brief example, but it's appropriately sized for a generic executor.

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 generic tool with 7 parameters, nested objects, and no output schema, the description is minimal. It doesn't mention response formats, error behaviors, or the requirement for mutation confirmation (which is in the schema but not the description). It relies heavily on midaz-discover to fill in details, making it adequate for a wrapper but incomplete as a standalone description, especially since it lacks any guidance on return values or failure modes.

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 100%: every parameter (resource, action, body, pathParams, queryParams, mutationReason, confirmMutation) has a description in the schema. The tool description does not add any parameter-specific meaning beyond what the schema provides. It only hints that discover is needed to determine parameters. Baseline is 3 for high coverage, and this tool meets that baseline without adding extra.

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 it executes Midaz API operations and lists supported resource types (organizations, ledgers, assets, etc.), giving a clear purpose. It distinguishes from the discover tool by explicitly directing to use midaz-discover first, but doesn't differentiate from sibling executors (e.g., fetcher-execute) beyond the Midaz domain, so it's clear but not deeply specific.

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?

Provides explicit usage guidance: 'Use midaz-discover first to find the right resource+action and required parameters, then call this tool to execute.' This clearly tells when and how to use it, and implies when not to (i.e., discovery should be done via midaz-discover, not here). It also mentions support for all CRUD operations, covering the scope of use.

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