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

Annotations declare readOnlyHint=true, which the description does not contradict. The description adds behavioral context beyond annotations: it explains that the tool returns delta vs full context depending on familiarity, and describes the session parameter as a branch label that shows neighboring sessions of the token. This provides useful behavioral disclosure beyond the read-only hint.

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 description is concise, containing only a few sentences. It front-loads the purpose and provides essential usage guidance. However, the language is somewhat dense and jargon-heavy (e.g., 'Курсора', 'полочки карты'), which could hinder clarity for an agent. Still, it is efficiently structured with no wasted words.

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?

The tool has an output schema, so return format is covered. The description covers when to use, how to use (delta vs full), fallback to get_project_context, and explains two of three parameters. It is fairly complete for an agent to call correctly, though the condition for 'many changes' is not precisely defined, and project_id semantics are assumed rather than stated.

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. It briefly explains 'since' (from the previous response's Cursor) and 'session' (label of your branch), but does not explain project_id, which is the only required parameter. While it adds some meaning to two of three parameters, it leaves the most critical parameter undocumented, so it only partially compensates for the schema 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 clearly states the tool's purpose: showing project changes since the last visit, listing specific content types (journal, assignments, files, map shelves, dialogs). It uses a specific verb (shows changes) and resource (project). However, it doesn't explicitly contrast with all sibling tools like list_files or read_journal, only mentioning get_project_context as an alternative, so it doesn't fully distinguish from every sibling.

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?

The description explicitly instructs when to call this tool: 'Call FIRST, as soon as you take on a project'. It differentiates between a familiar project (only delta) and a first-time visit (full context). It also provides a fallback: if it says 'many changes', then get get_project_context. This is clear, actionable usage guidance with explicit alternatives.

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