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

Annotations already declare readOnly=true, destructive=false and openWorld=false, so the safety profile is covered. The description still contributes non-obvious behavior: a 300s tenant cache (implying possible staleness), versioned provider metadata, and the semantic warning that a queryable field is not necessarily mutation-eligible. It stops short of saying what happens with unknown or invalid names, which matters for a batch call.

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?

Two tight sentences, front-loaded with the capability and its limits, with no filler. The closing caveat is slightly cryptic in isolation, but it earns its place by warning about a real misuse mode.

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?

An output schema exists, so return values need not be described. However, for a batch lookup of up to 50 exact names, the definition never says how partial failures or unknown names are handled, nor what the cache window means for freshness-sensitive callers. Adequate, but with gaps an agent would hit on first use.

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 only 33%: customer_id is documented inline and connection_context is not, so the description must carry weight. It does clarify that names are exact (not fuzzy) and caps the batch at 50, which refines the names array beyond its schema constraints. It says nothing about the format or role of connection_context, leaving a third of the parameters undocumented in either place.

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 a specific verb and resource ("resolve ... exact field names") and enumerates what comes back: versioned provider metadata, compatibility, enum values. That is concrete enough for an agent to know this is a metadata lookup, not a data query. It never names a sibling it is distinct from (e.g. google_ads_query_preflight or google_ads_creation_capabilities_get), so differentiation is inferred rather than stated.

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?

"Resolve up to 50 exact field names" implies the use case (validating/looking up field names before building a query), and "Queryability is not mutation eligibility" flags a caution, but the definition never states when to pick this over the many neighboring metadata tools. There is no explicit when-to-use or when-not-to-use statement and no named alternative.

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