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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful behavior: values are percentages 0-100, and nulls mean Microsoft reported no value due to insufficient traffic — a critical detail for an agent parsing results. It doesn't cover row count or ordering, but the schema's limit parameter does.

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 tightly packed sentences with zero filler: the first defines scope and output, the second defines the null/percentage semantics and the action implied by each loss metric. Scope is front-loaded ahead of interpretation.

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 does the work of explaining what comes back: three percentage metrics, per-campaign granularity, and null semantics. It is missing only the row identity/ordering detail (highest spend first, capped by limit), which is present in the schema rather than the description.

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 every parameter (limit, startDate, endDate, accountId) is already documented with formats and defaults. The description only echoes the date-range concept without adding syntax or default behavior. Baseline 3 is correct when the schema carries the parameter burden.

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 impression share per campaign for a date range') and enumerates the returned metrics: share, share lost to budget, share lost to rank. The reference to 'Microsoft reports' ties it to the Microsoft Advertising platform, but it never names the sibling get_impression_share to distinguish the two, so differentiation is implied rather than explicit.

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?

Usage is only implied: an agent can infer this is the tool for impression-share reporting per campaign. There is no explicit 'use this when... / not when...' statement and no pointer to alternatives such as msads_get_campaign_performance or the generic get_impression_share. The diagnostic sentence ('Low share lost to budget means raise budget') is interpretive advice, not invocation guidance.

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