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

Annotations already establish readOnly/openWorld/destructive=false, so the safety profile is covered. The description adds a genuinely useful behavioral fact the annotations don't carry: quality score is null for keywords with too little traffic, which prevents the agent from misreading nulls as errors. It does not mention pagination or how many rows are returned before the limit applies.

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?

A single dense sentence, front-loaded with scope before metrics, with the null caveat trailing as a separate sentence. The metric enumeration is long but each item is a real return field the agent would otherwise have to guess at, given there is no output schema.

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 must describe return shape, and it does so field by field including the quality-score sub-ratings and the null case. Defaults and account resolution live in the schema, so nothing essential is missing; only pagination/row-count behavior is left implicit.

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 all five parameters — including date defaults, accountId sourcing, and the campaignId provenance — are already documented in the schema. The description only echoes "optionally one campaign" and the highest-spend ordering. Baseline 3 is correct where the schema carries the load.

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 names a specific resource (keyword performance) and enumerates exactly what comes back — match type, quality score with component ratings, bid, and the standard metric set. That is well past tautology and clearly distinct from a plain keyword-list tool. It stops short of naming the sibling it differs from (msads_get_keywords, msads_get_ad_group_performance), leaving the agent to infer the level of granularity.

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?

"For a date range (optionally one campaign)" implies the scoping context, and the "highest spend first" framing hints at the analysis use case. There is no explicit when-to-use versus msads_get_keywords or msads_get_ad_group_performance, and no stated preconditions. Usage is inferable but not guided.

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