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

Annotations already declare readOnlyHint=true, openWorldHint=true, destructiveHint=false, so safety and live-network behavior are covered structurally. The description adds genuine context beyond that: it queries the live gallery shared with Tag Manager's Search Gallery and additionally reports which templates are already imported into the container's Caybl workspace — a non-obvious side effect of the read. It stops short of describing the returned fields (template ids needed for the follow-on import call) or any rate/limit behavior, so it adds value but not full behavioral depth.

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-loads the core action and the pre-Custom-HTML timing, then layers parameters, preference rule, and next steps — a sensible order with little waste. Minor redundancy in the parenthetical 'live, the same list as Tag Manager's Search Gallery' and the 'Caybl workspace' aside, which dilute an otherwise tight statement.

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?

With no output schema, the description carries the burden of explaining return values, and it only gestures at them ('finds templates for the vendors in it', 'shows which templates are already imported'). For a discovery tool that feeds gtm_import_template, the agent would benefit from knowing what identifying fields come back; the workflow guidance partially compensates, so this is adequate but not complete.

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 coverage is 100% and already documents all four parameters, including the query examples and the snippet semantics, so the description largely restates them. It adds only the either/or framing of query versus snippet ('Give `query` ... or paste a `snippet`') and says nothing about the container or workspace parameters, so it does not meaningfully exceed the schema.

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 ('Search Tag Manager's own Community Template Gallery') and scopes it precisely to the live gallery, which is distinct from any local-only list. It also names the concrete downstream tools (gtm_import_template, gtm_upsert_tag kind=template), so an agent can place it in the workflow 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?

Explicit timing ('BEFORE writing Custom HTML'), explicit preference rule ('Prefer the official template, usually owned by the vendor'), explicit sequencing to the next two tools, and an explicit fallback ('If nothing matches, propose Custom HTML'). This is a complete when/when-not/alternatives statement.

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