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

Annotations already cover the safety profile (readOnly/idempotent/non-destructive), and the description adds behavior beyond them: default returns top 5 recent runs, aggregate mode returns named stat fields (testCount, sumSuccessMeanSecs, slowTestCount), and a warning about env scoping distorting results. Missing any note on pagination interplay between limit/offset and the 'top 5' default.

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?

Dense but well ordered — addressing mode first, selection preference second, narrowing filters third, aggregate mode last. Every clause carries information; the one weakness is that it is a single run-on paragraph whose conditional clauses ('or a scenario when scenarioId is set') require careful parsing.

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 15-parameter, no-output-schema, nested-object tool, the description covers the main selection axes but leaves pagination (limit/offset), the timeWindow structure, and the release/branchId relationship unexplained. An agent could call it correctly for the common case but would likely guess wrong on time-windowed or paginated queries.

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 only 13% across 15 params, so the description carries a heavy burden and does partially meet it: it explains testId, scenarioId, scope.filePaths/folderPath, platform, dimensionFilters, aggregate, branchName and environment. But limit, offset, timeWindow (fixed vs relative), release, branchId, botId and projectApiKey are left entirely to the bare schema, including the ambiguous relativeWindow string.

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?

Opens with a specific verb+resource ('Fetch SmartTest execution history') and enumerates the three addressing modes (testId, folder/file scope, scenarioId). It references fetch-execution-report as the source of testId, which implicitly distinguishes it from that sibling, though it never states explicitly how the two differ in output.

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 concrete routing advice: 'Prefer testId when you have it from fetch-execution-report', 'Typically omit environment to avoid env scoping', and 'Set aggregate=true for suite timing stats instead of per-test history'. That is real when-to-use guidance with a default choice, though it stops short of stating what to use when no testId/scenarioId/scope is available.

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