Add a question from a description

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

Goes far beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false): it enumerates validation codes that write nothing (SPEC_INVALID, CODE_CONFLICT, SURVEY_ACTIVE, etc.), the import_question side effect on translation gaps that 'cannot be undone', the rollback behavior on post-import failure (delete-and-report), and the unknown-outcome path where nothing is deleted. It also names the required write scope, which the annotations do not convey.

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?

Purpose is front-loaded, but the remainder is a dense, comma-chained wall of edge cases and error codes with little structural separation. Every clause is informative, yet the run-on delivery makes it hard for an agent to parse; bullets or grouping of the failure paths would help.

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 complex mutation tool with nested spec objects, validation, rollback, and irreversible side effects, the description is thorough. Return-shape detail is somewhat redundant given the output schema exists, but completeness for correct invocation is not in question.

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 description coverage is 100%, so the schema already documents all parameters. The description nonetheless adds meaning the schema lacks: the code must be free across the whole survey case-insensitively, the spec is one string or a per-language map, and the acknowledge/fill_translation_gaps semantics. This is above the baseline but position formatting largely repeats the schema.

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 a precise verb+resource+constraint: 'Insert one new question into a group of an inactive survey, described as a question spec.' It also distinguishes itself from the relevant sibling by noting 'A whole group goes with limesurvey_add_group_from_spec,' so an agent can separate this from add_group_from_spec and update_question_from_spec.

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 preconditions and routing: 'an inactive survey' is required, 'An active survey is refused,' the spec must come from limesurvey_get_survey_spec at level question, and whole-group insertion is redirected to limesurvey_add_group_from_spec. The acknowledge flag is also tied to a specific risky condition, making the when-to-use conditions clear.

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