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

The description discloses far more than annotations: retry semantics with key dedup, duplicate creation without key, manifest write-list gating, read-list restrictions causing row_not_found, and the return shape. Since annotations only provide generic hints (readOnlyHint false, idempotentHint false), this description carries the full behavioral burden and does so excellently.

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 long but every sentence contributes valuable information: core behavior, key semantics, retry behavior, permissions, access-control edge cases, and return shape. It is front-loaded with the main action and no sentence is filler. The structure is logical and appropriately sized for the tool's complexity.

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?

Despite no output schema and sparse annotations, the description covers all essential context: the dedup behavior, key-based retry safety, prerequisites (manifest write list), access-control consequences, and return payload. It also mentions edge cases like row_not_found. This is complete for an upsert tool with subtle permission and idempotency considerations.

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?

The schema already describes all four parameters with 100% coverage, so the baseline is 3. The description adds meaningful context beyond schema definitions, especially for `key`: it explains that omitting it creates a server-generated key and that retrying with an omitted key produces a duplicate. This extra guidance justifies a score above baseline.

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 action: 'Create a row in a v2 app's collection, or return the existing row when `key` is already present (deduped:true).' It clearly identifies the resource (v2 app collection), the verb (create/upsert), and differentiates from siblings like get_row and update_row by noting there is no separate strict-create verb. This is a specific and unambiguous statement of purpose.

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 provides strong guidance on when to use it: omit `key` for a new row with a server-generated key, or pass `key` to ensure existence and make retries safe. It also explains access-control preconditions (manifest write list) and read-list behavior. However, it does not explicitly contrast with sibling tools such as 'use get_row for reads' or 'use update_row for modifications,' so it falls just short of full alternative differentiation.

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