record

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

The description reveals important behavioral details beyond the minimal annotations: download_image writes a file via outPath, save_to_person creates citations and merges events, updateExisting replaces facts, saveAsAlternate keeps both, and includeRelatives adds/linked relatives. Some actions such as image_index and shoebox_remove get only terse mentions, so it is not fully exhaustive.

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?

The description is dense and front-loaded with the overall scope, then organized by action. There is no filler, but the long run-on sentence with semicolons and nested parentheticals makes it harder to parse quickly.

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 15 parameters, 8 actions, and no output schema, the description covers the critical return/effect semantics for get, download_image, suggest_places, and save_to_person. However, image_index, shoebox_list, shoebox_save, and shoebox_remove lack comparable detail, and some parameter-purpose relationships are left to inference.

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 only 27%, but the description compensates by explaining key parameters: maxSide and outPath, events options and default, updateExisting/saveAsAlternate/updateName semantics, includeRelatives usage, and suggest_places term. A few parameters like title, collectionId, and recordId remain semantically thin or unexplained.

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 clearly identifies a resource ('Historical records and places') and enumerates specific actions with concrete verbs and object details (get, image_index, download_image, save_to_person, suggest_places, shoebox_*). It is unambiguous about what the tool does, though it does not explicitly differentiate itself from sibling tools like search_records.

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?

Each action carries enough context to imply when it is appropriate, e.g. 'save_to_person ... exactly like the site Review page' and 'suggest_places ... place autocomplete → gpid'. There is no explicit when-to-use versus sibling alternatives or when-not-to-use guidance, so usage is implied rather than stated.

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