create_taxtable

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

Annotations only convey generic traits (mutating, non-idempotent, non-destructive). The description goes well beyond them by disclosing posting-time side effects (multi-entry composites produce multiple tax splits per line), the name-uniqueness constraint, the same-commodity requirement across accounts, and the ASSET/LIABILITY account restriction. No contradiction with 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?

Well-structured and front-loaded: one-sentence purpose, a tight domain-context paragraph, a formatted Args section, and a complete runnable example. The length is justified by the complexity the schema fails to capture; no sentence is redundant.

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?

Complete for a moderately complex create tool: purpose, every parameter and sub-field, constraints, side effects, and a worked example are all present. The output schema covers return values, and annotations cover the safety profile, so nothing an agent needs to invoke this correctly is missing.

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 0% and the entries parameter is an untyped shell (additionalProperties: true), so the description carries the full burden and succeeds. It documents name uniqueness with concrete examples and fully specifies the entries dict structure, including the crucial pitfall that percentages are rates ('5.00' = 5%, not '0.05') and the accepted account reference formats.

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?

Opens with the specific verb+resource 'Create a new sales-tax table' and then elaborates what a taxtable is and how entries behave. This clearly distinguishes it from the sibling CRUD tools list_taxtables, update_taxtable, and delete_taxtable.

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?

Usage is implied through the create verb and the thorough domain explanation, but there is no explicit routing to alternatives such as update_taxtable for modifying an existing table or list_taxtables for discovery. No preconditions, exclusions, or 'use this when' guidance is stated.

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