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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, but the description adds genuine behavioral context: ids are read from the client's linked Analytics property and Google Ads account, nothing is installed by this tool, and the caller must place the snippets, deploy, and verify with site_check. It does not specify failure modes when the client has no linked account, which is the main remaining gap.

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 audience ('For a client's website that the agency edits in CODE'), then the deliverable, then where ids come from, then the read-only constraint and handoff. Dense but each clause carries information; the parenthetical tech list and 'plain HTML…' are the only slightly padded elements.

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 compensates by enumerating the returned snippet types and noting each comes 'with where it goes', plus disclosing the id source and the downstream verification step. An agent knows what it gets back, what it must do next, and that nothing is mutated — sufficient for a five-parameter read-only tool.

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 100%, so each of the five parameters is already documented (including that form_label and phone_click_label are overrides). The description explains where the ids originate and names the conversion types, but adds no per-parameter syntax, format, or default detail beyond the schema — baseline 3 is appropriate.

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 ('return the tracking snippets with the client's real ids filled in') and enumerates exactly what is returned: Google tag, form-lead conversion, phone-tap conversion, tap-to-call link, Search Console verification tag. The scoping clause 'a client's website that the agency edits in CODE' implicitly separates it from the WordPress sibling wp_install_tracking, so an agent can route correctly 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?

Gives clear context for use (code-built sites: Claude Code, Codex, Next.js, Astro, plain HTML) and the surrounding workflow — assistant places the snippets, deploys, then site_check verifies. It stops short of an explicit 'when not to use' (e.g., use wp_install_tracking for WordPress sites), leaving that exclusion to inference from the 'in CODE' qualifier.

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