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

The description discloses extensive behavioral details beyond the annotations: MERGE semantics (only fields sent change), list replacement vs append behavior, caps (100 companies, 25 posts, 25 anchors), unknown-field refusal, side effects on save (creates row if none, makes lane due, resets retry backoff, forgets cached misses), and the refusal condition for `on: true` when nothing would run. It also clarifies that no execution happens inside the call. These add substantial context on top of the annotations (readOnlyHint false, destructiveHint true, idempotentHint true) without contradicting them.

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?

The description is dense but every sentence carries weight. It front-loads the purpose, then systematically covers merge semantics, list behavior, caps, unknown-field handling, save side effects, the `on` flag, execution behavior, and a pointer to the reference. There is no filler; each clause adds a distinct operational fact. The structure flows logically from core semantics to edge cases to routing.

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 tool with 5 parameters and a nested config object, the description covers nearly every aspect an agent needs: merge semantics, caps, refusal conditions, side effects, execution timing, and a reference pointer for field meanings. It even hints at the response via `truncated`. Given the lack of an output schema, this description provides sufficient context to call the tool correctly and predict behavior. It is complete for the tool's complexity.

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%, so the baseline is 3. The description adds meaningful semantics beyond the schema: it explains MERGE behavior for config fields, specifies caps (e.g., max 25 posts/anchors, 100 companies) that are not in the schema, clarifies the default listMode and its interaction with `truncated`, and describes the `on` parameter's refusal condition. This supplements the schema descriptions, which are already detailed but lack the interaction rules. It earns a 4 for adding value beyond 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?

The description opens with a specific verb+resource ('Write a lane's settings') and enumerates concrete actions (upload account list, set intent and anchors, change keywords, move a gate). It clearly distinguishes this from siblings like gtm_run_source by stating it writes configuration rather than running anything, and it mentions the reference tool gtm_sources_reference. This leaves no ambiguity about what the tool does.

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?

The description explicitly states when not to use it: 'Nothing runs inside this call: an ON lane on an ACTIVE play runs on the next tick (≤5 min); otherwise use gtm_run_source.' It also directs the agent to read gtm_sources_reference for field meanings, providing a clear alternative for deeper context. It explains when the `on` flag is appropriate and when it will be refused, giving actionable usage guidance.

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