sb_function

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

Annotations already flag destructiveHint and openWorldHint, and the description adds real value on top: it discloses the permission model, that functions run with the site's secrets/collections/fetch, that 'remove' deletes, and that 'test' actually invokes the function with a method/path/body. It does not explain dry_run, which is the one safety-relevant gap for a destructive tool with a test path.

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?

Extremely dense but earns nearly every token; the resource definition and the sb_code exclusion are front-loaded before the action map. The action list is crammed into a single run-on clause, which slows parsing for a 17-parameter tool but wastes little space.

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 an eight-action, 17-parameter tool with no output schema, the description covers the core dispatch logic and the risky operations well. It falls short on parameters that gate behavior (dry_run, enabled, language, site_id) and does not say what list/get/logs/usage return, leaving genuine holes.

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 6% (only 'id' is annotated), so the description has to carry the load and it does for the ambiguous cases: id-vs-create/merge on set, key+value on secret, and the full test payload shape. However six parameters (dry_run, enabled, language, content, limit, site_id) are never mentioned anywhere, including the limit's 1-200 bound, so an agent still guesses at them.

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 definition names the resource and its runtime ('server-side TS/JS at /_wb/fn/<slug>') and immediately differentiates it from the nearest confusable sibling with 'Not sb_code'. An agent can decide between sb_function and sb_code without opening either 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?

It gives an explicit exclusion (not sb_code) and an authorization precondition ('Owner/admin only'), plus action-level guidance embedded in the list (no id creates; id merges). What is missing is any statement of when a given action should be chosen over a sibling like sb_add or sb_set, which is left implicit.

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