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

With no annotations, the description carries the full burden and does well: it discloses that each row is validated against the table's schema, that a type mismatch fails the entire call with table_schema_violation, and that nothing is written (atomic semantics). Permission and rate-limit behavior are not covered, but the key mutation semantics are.

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?

Two front-loaded sentences with zero waste: the first defines the operation and accepted input shapes, the second defines validation and failure behavior. Nothing redundant.

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 three-parameter mutation with a fully documented schema and no output schema, the description covers purpose, input shapes, validation, and error/atomicity semantics. The only gap is that it doesn't explain how to create a table first or how this differs from sibling insert tools.

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%, so all three parameters (rows, table, tenant_key) are already documented, including the header-precedence rule for tenant_key. The description adds no parameter detail beyond what the schema provides, 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?

States a specific verb (append) and resource (rows to a declared table), and clarifies that rows may be a single object or an array. It does not explicitly distinguish itself from the similar sibling host.state.insert, so the agent must infer the difference from the 'declared table' phrasing.

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?

Usage is implied: 'declared table' signals a prerequisite that the table must already exist via host.table.create, and the schema handles the tenant_key auth condition. However, there is no explicit when-to-use guidance or named alternative (e.g., host.state.insert, host.table.query) to route the agent.

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