get_changelog

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

With no annotations, the description carries the full behavioral burden and does so well: newest-first ordering, per-event attribution (app vs named agent), and an explicit pagination contract ('before=<_meta.next_before>, never an offset'). It omits auth/permission requirements and default page size, so not quite maximal.

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 front-loaded: identity and ordering first, then the deleted-node rationale, then filters, then pagination, then the undo path. Every clause adds operational detail rather than filler.

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?

Rich enough for an 8-param read tool with no output schema and no annotations, covering return ordering, filtering, pagination, and a cross-tool workflow. The main holes are the undocumented limit and projectId parameters and the absence of any authorization note.

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 0%, so the description must compensate, and it documents 6 of 8 params including enum-like values absent from the schema (action add|update|delete|restore, source app|api_key, ISO format for since/before). It leaves limit and projectId entirely undocumented, a real but modest 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?

States a specific verb (Read) and resource (the plan's history) and enumerates the event types (add/update/delete/restore) plus attribution. It further distinguishes itself from sibling list_nodes by explaining changelog is the way to find a node after deletion, which /nodes cannot do.

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?

Explicitly states when to use this over /nodes ('find a node AFTER it was deleted') and routes to the follow-up tool ('undo with mutate {action:restore, nodeId}'). It even specifies ordering within the restore (parent before children), leaving little to inference.

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