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

Annotations already declare read-only, idempotent, non-destructive, but the description adds substantial context beyond them: the 60-row cap, newest-first ordering, the 30-day default window, that only real moves are returned by default, what include_wording unlocks, and the dataset coverage limitation. That is exactly the behavioral detail an agent needs.

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-loads the core purpose and dataset scope, then the return shape, then usage. It is dense and the long enumeration of returned fields is somewhat list-heavy, but every element carries information about what an agent will get back.

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's enumeration of returned fields (since, count, changelog, changes with date/tool/plan/field/old/new/source/method/note/page) fills that gap. Combined with the dataset limitation and default filtering, an agent has everything needed to call it correctly.

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 the baseline is 3; the description adds value by explaining the default look-back window (30 days) and by characterizing include_wording as re-verification rows for wording-only or first-recorded values, which is richer than the schema's wording.

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 ('read-only dated change log') and immediately scopes it to the ai-plans dataset, noting other datasets have no history. It also distinguishes itself from siblings by naming get_tool as the tool to cross-check figures against.

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 usage examples ('what changed in the Claude plans this month') and an explicit cross-check scenario with get_tool. It clarifies the default filter (real moves only) and how include_wording broadens scope, but does not explicitly state when not to use it versus compare_tools or search_limits.

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