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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, and the description still adds real behavior: it lists the concrete deliverables (landscape PDF with Ahnentafel numbers and blank boxes, ancestor list page, Excel export, data checks for broken links and impossible dates) and confirms the source file is never changed. It also discloses the disambiguation flow when multiple people share a name, which is not derivable from any structured field.

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?

It is front-loaded with the "Use this when..." trigger and the exclusions land at the end, which is the right order for an agent scanning for eligibility. It is one dense run-on paragraph where the return-value catalog and the exclusion clause compete for attention, so a small structural penalty is warranted.

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?

An output schema exists, yet the description still summarizes the deliverables and adds the data-check behavior the schema cannot convey, plus the clarification loop for ambiguous names and the guest-file constraints. Completeness is high for a 5-parameter, nested-object tool; only the sibling-tool relationship is unaddressed.

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% and each parameter already carries a rich description, including the file-vs-gedcom_text preference and the 4-6 generation range. The description summarizes the same hints (file or gedcom_text, person by name or ID, 4 to 6 generations) without adding format or edge-case detail beyond the schema, so the baseline 3 applies.

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 opens with a precise verb and resource ("generate a pedigree chart" from a GEDCOM file) and enumerates the user phrasings it covers, so the agent can match intent confidently. It never names the sibling tool convert_gedcom_to_excel, even though it also produces an Excel file, so the boundary between the two tools is left implicit.

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?

It gives explicit positive triggers (pedigree/ancestor chart, printable family tree, "a chart from my GEDCOM file") and explicit exclusions (does not research ancestors, does not add people, not for a tree described only in words). It also handles the ambiguous-name case by telling the agent to list matches and ask the user. The only missing element is guidance versus the sibling convert_gedcom_to_excel.

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