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

Annotations are all false defaults and convey nothing, so the description carries the full burden and delivers richly. It discloses metadata stripping via WebP re-encoding, cross-system writes to CRM person_photos, avatar behavior for set_as_avatar=true, the $0.15 cost, and the API key requirement — all material traits an agent cannot infer from schema or annotations.

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?

Four short sentences with the core purpose front-loaded, followed by input modes, transformation behavior, side effects, then cost/auth. Every sentence contributes a distinct fact with zero 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?

An output schema exists, so return values need not be covered. The description adequately addresses inputs, re-encoding, side effects, cost, and auth. Minor gaps: valid entity_type values and behavior when both image_base64 and url are supplied are not stated, though both are inferable from the schema and phrasing.

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 reported at 100%, so baseline is 3. The description adds genuine meaning beyond the schema by stating the exclusivity constraint ('one required' between image_base64 and url), which the anyOf alone does not make explicit, and by explaining the behavioral effect of set_as_avatar for person uploads. entity_type/entity_id semantics remain only implicit via 'Life Graph entity'.

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 ('Upload a photo to a Life Graph entity') and clarifies the two accepted input modes. The WebP re-encoding detail distinguishes it from generic sibling upload_asset, though no sibling is explicitly named.

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?

Offers input-mode guidance ('image_base64 or url (one required)') and explains the conditional behavior for person uploads (CRM gallery, avatar). However, it never names upload_asset or attach_asset as alternatives or states when to choose them, so sibling routing is left to inference.

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