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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, and the description adds the non-obvious behavioral contract: no JSX/CSS/code generation, optimistic concurrency via expected_revision (0 only when absent), table_version_id must equal live_version_id, existing bindings survive compatible refreshes, incompatible visible columns fall back to Table, and changes never touch search/sorting/filtering/access. It even documents a failure mode (view_changed → reread before retrying).

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?

Front-loaded with the action and prerequisites, and nearly every sentence adds a distinct operational fact. It is dense — several long compound sentences about revisions, versions and fallbacks could be split for scanability — but there is no 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?

For a 6-parameter, nested-object mutation tool with no output schema and zero schema descriptions, the description supplies the preconditions, the concurrency model, the dry-run path, the return value (saved record_presentation) and the retry behavior. Nothing an agent needs to call it correctly is missing.

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 0%, so the description carries the full burden and does: it explains expected_revision semantics, the live_version_id constraint on table_version_id, the meaning of dry_run (verify authorization, serving version and schema without saving), and the template choice plus the approved field-role binding vocabulary that the bare schema only enumerates.

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 — saves one versioned contextual view for a table — and clarifies the versioning scope ('after its first successful build'). An agent can distinguish it from siblings like get_table, configure_table_search, and generate_cover without opening a schema.

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?

Explicitly prescribes the workflow ('inspect its intent, actual schema and a bounded sample first'), states when to prefer the plain 'table' template, and gives the otherwise branch with the approved role list. It also names get_table as the source for record_presentation and its revision — a real alternative/companion, not just a restated purpose.

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