Check configuration

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so 'Read-only, writes no files' adds little. The description does go beyond them with substantive behavior: structural-only checking (no cell values read), no totals computed, and reporting of typos/fallbacks rather than failing, which tells the agent to expect a diagnostic report rather than an error.

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?

Front-loaded with the action and the report contents, then exclusions, then the alternative and side effects — a sensible order. It is dense and the long enumerations make it slightly heavy, but no sentence is redundant except the mild overlap with the readOnly annotation.

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 3-parameter read tool with an output schema, the definition covers inputs, the shape of what is reported, the structural-only limitation, the sibling alternative, and side effects. An agent has everything needed to choose and invoke it correctly.

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%, so the baseline is 3, but the description adds real meaning about what each input yields: configPath/configYaml produce an effective-settings and field-mapping report, while csvPath triggers a header-vs-referenced-columns comparison listing missing and unused columns. That is more than the schema's generic 'structural check' note.

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?

States a specific verb and resource ('Loads a YAML configuration ... and reports its structure') and enumerates exactly what the report contains (effective settings, mapped fields with sources, unknown keys, out-of-set values with CLI fallback, ignored/missing sections). It is clearly distinguishable from siblings such as config_schema_get and config_file_create, and even names the alternative invoice_get.

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?

Gives explicit exclusions ('does not read cell values', 'does not calculate totals') and routes to csv2zugferd_invoice_get for a trial run. It does not, however, contrast with the closest sibling csv2zugferd_config_schema_get, so an agent must infer that boundary itself.

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