sb_code

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

Annotations already declare destructiveHint=true, openWorldHint=true and readOnlyHint=false, so the safety profile is covered; the description adds the non-obvious merge semantics of 'set' with an id (partial update over the stored row), which is real behavioral value beyond annotations. It does not, however, spell out the consequences/dry_run behavior of removal.

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?

Dense but efficiently front-loaded: resource identification first, then placement, then action semantics, then the exclusion. No filler, though the action clause is crammed and slightly harder to parse than it needs to be.

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?

Against 11 parameters, 9% schema coverage, no output schema and a destructive annotation, the description covers the resource and action semantics well but leaves several parameters (dry_run, enabled, language, position) undocumented and says nothing about return shape or rollback. Adequate but with clear gaps for a tool this size.

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 only 9%, so the description must carry parameter meaning, and it explains the key ones: placement values (head/body_start/body_end), page_id scoping (site-wide vs one page), and id create-vs-merge semantics. It leaves dry_run, enabled, language, position, name, content, and site_id unexplained, so compensation is partial.

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 resource (the site's custom code files) with concrete examples (tracking pixels, analytics, chat widgets, site-wide CSS) and the placements where they are injected. It also explicitly excludes 'the custom-code element,' though it never names a sibling tool by name. Purpose is clear and diagnosable, just lacking direct sibling routing.

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?

Guidance for the action lifecycle is explicit: 'list', 'set' (no id creates; with id merges named fields over the stored row), 'remove', and page_id''s dual scope (site-wide when absent). This tells the agent how the modes differ, but there is no when-to-use-vs-alternative guidance against nearby tools like sb_set/sb_remove.

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