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

With readOnlyHint=true already covering safety, the description still adds substantial behavior: default 20 newest revisions, hard cap of 50 with the stated rationale (protecting model context), newest-first ordering, and the meaning of the isCurrent flag. It does not cover auth/permission needs or what happens with an out-of-range version number, which keeps it just short of a 5.

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 scope, then pagination strategy, then workflow routing, which is the right order. It runs long with some redundancy — the 'never reuse the open page revision id' warning is restated across adjacent sentences — but nearly every sentence carries operational information.

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?

No output schema exists, so the description has to describe returns, and it does: version number, revisionId UUID, and isCurrent, plus the distinction between user-facing version numbers and machine revisionIds. The one gap is the strategyId/aiStrategyId parameter distinction, which stays undocumented for a tool that accepts both.

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 60%, and the description compensates for the important half: version-vs-limit/offset precedence and the 'ignored when version is set' interaction are spelled out clearly. However, strategyId and aiStrategyId carry no description in either schema or prose, and their relationship to the 'named target strategy' guidance is only implied.

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 opening sentence names a specific verb and resource ('Returns a bounded page of available revisions for a strategy') and immediately pins the two identifying fields (revisionIds and version numbers). It also distinguishes itself from siblings by naming set_strategy_revision, switch_active_strategy, create_strategy, and get_file as the tools this one feeds rather than replaces.

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?

Explicit routing: use version=<n> when the user names an exact historical version, use limit/offset only for browsing unknown older history, call list_strategies first when a named strategy differs from the open page, and call create_strategy first for first-build work. Each alternative is paired with the condition that selects it, plus an explicit prohibition against reusing the open page revision id.

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