plan_log

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

With no annotations, the description carries the full burden and largely succeeds: it discloses that undo/restore are non-destructive (they write a NEW version), that both require base_rev and merge like any other edit, and that forgotten plans remain retrievable so a forget can be undone. It omits permissions/auth requirements and rate limits, but the core behavioral traits are well covered.

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?

The listing behavior is front-loaded in the first sentence, with the mutation semantics following as supporting detail. Every sentence conveys distinct information with no filler or redundancy.

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?

Given 9 parameters, no annotations, and no output schema, the description is fairly complete: it describes the return ordering ('newest first'), the attribution ('who changed what'), and the mutation semantics. The main gaps are the undocumented save parameter and the lack of any note on how as_of/since interact with the returned rows.

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?

At 67% schema coverage, the schema already documents undo, restore, base_rev, as_of, limit, and since. The description meaningfully adds to the schema by clarifying that undo/restore create new versions rather than rewriting history and that they merge through the normal edit path. It leaves save and world undescribed in both places, so it does not fully compensate for the coverage gap.

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 states a specific resource and scope: 'One plan's versions, newest first: who changed what, from chat or from the page.' This clearly sets it apart from the sibling list_plans, which lists plans rather than the version history of a single plan. However, it never names list_plans or diff_vs_save as the alternatives, so the differentiation is implicit 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?

It gives good usage guidance for the mutation paths, explaining that undo=<v> and restore=<v> both require base_rev and merge like any other edit. But it offers no guidance on when to reach for plan_log versus list_plans, diff_vs_save, or site_plan, which is the primary routing decision an agent faces.

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