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

Goes well beyond the destructiveHint=true annotation: deletion is permanent ('a deleted row cannot be restored by any tool'), ops can only touch rows this agent wrote, writes are upsert, batch size is capped at 50, and `atomic` governs all-or-none versus partial batches that answer `complete: false`. It also discloses the attribution string applied to each row, which no structured field conveys.

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?

A single dense paragraph front-loads the purpose and then packs limits, mutation semantics, and warnings into semicolon-separated clauses with no filler. It is telegraphic in places ('≤50 a call') but every clause carries information an agent needs.

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 destructive, no-output-schema write tool this covers permissions, irreversibility, batch limits, partial-failure signaling, and the sibling escape hatch for visitor rows and content entries. Missing are the shape of a successful response and the rows/ops interaction, which are the only remaining ambiguities before calling it.

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?

With only 20% schema description coverage, the description carries most of the load and does so well: it defines the `ops` object shape ({op: create|replace|delete, id, row, stream}), the `stream` scoping behavior, the `atomic` semantics, and the 50-item cap. The one gap is that it never says whether `rows` and `ops` may be combined in one call or are mutually exclusive.

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 ('Write rows into an artifact') plus a permission qualifier ('this key may edit'), so an agent knows exactly what it does. It also partially disambiguates from neighbors by noting that content-collection entries belong to super_entries, though it never contrasts itself with super_data or super_artifacts by name.

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?

Gives concrete routing rules: 'Visitor rows are never changed here' and 'entries of a content collection are super_entries' explicitly push those cases elsewhere. It also distinguishes the `rows` path (creates in `stream`) from the `ops` path (replace/delete of the agent's own rows), which is real usage guidance, but there is no explicit 'use this instead of X when...' framing.

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