add_person

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

Annotations already declare the write/non-idempotent/non-destructive profile, so the bar is lower. The description adds real behavioral value beyond them: the call can FAIL when require_citation is True and no citation is supplied, and the unsourced alternative stamps an UNSOURCED attribute detectable by list_unsourced_facts. It further states the return payload (handle and gramps_id).

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?

Three short paragraphs, front-loaded with the core action before the citation-practice guidance, and every sentence carries actionable content. Slightly more text than strictly needed for a single creation tool, but nothing is filler.

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?

No output schema exists, but the description names the return values, and given the very rich nested input schema the citation workflow is fully covered. Remaining gap: no note on duplicate detection or how this interacts with find_duplicates/merge_objects for a non-idempotent create.

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. The description nonetheless adds operational meaning to require_citation (it is a hard failure gate, not just a flag) and to the citation field (cite the specific record that proves the fact, set confidence honestly), which the schema alone does not convey.

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 ('Create a new person') plus the optional scope (cited birth/death events), which cleanly distinguishes it from siblings like add_family, add_event_to_person, and update_person. An agent can pick this out without opening the schema.

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 clear context ('Use this to add someone to the tree') and a decision rule for the citation case vs. the legacy-hint case with require_citation=False. It does not name sibling alternatives such as add_event_to_person for adding events to an existing person, so routing is implied rather than explicit.

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