media

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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description adds meaningful behavioral detail beyond that: download can write to outPath or return base64 with maxSide scaling, upload maps a local file to a person gallery, update keeps omitted fields, and copy_from_tree only works from a public tree. No contradiction with the annotations was found.

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 packs an entire multi-action API into a single compact sentence, with each action clause earning its place. It is dense and could benefit from line breaks, but it is efficient and front-loads the resource type before detailing the actions.

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 tool with 19 parameters, 8 actions, no output schema, and only 21% schema-description coverage, the description provides a decent action roadmap but is incomplete. It omits return-value information, per-action required parameters, pagination behavior, and the meaning of cropping and primary-photo parameters, which an agent would need to invoke the tool correctly in many cases.

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 21%, so the description must compensate, and it does cover several parameters by embedding them in action explanations: outPath, maxSide, filePath, personId, title, date, description, location, and destPersonIds. However, key parameters such as mediaId, cropX, cropY, cropSize, page, sourceTreeId, sourcePersonId, and asPrimaryPhoto are left completely unexplained, and it is unclear which parameters each action requires.

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 the resource domain ('Photos, documents and stories in a tree') and then enumerates eight specific actions as verb+resource pairs: list, get, download, upload, update, set_profile_photo, copy_from_tree, delete. It even differentiates from sibling fact by pointing out that attaching media to a fact is fact.attach_media. An agent can tell exactly what this tool is for.

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?

The description gives contextual usage hints for many actions, such as listing for a person vs. the whole tree when personId is omitted, copying from a member's public tree into destPersonIds, and that update preserves omitted fields. It also explicitly routes fact attachment to fact.attach_media. It lacks broader when-not-to-use guidance versus all siblings, but the action-specific notes are strong.

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