get_issue_history

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

The annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false) already convey that this is a safe, non-mutating read operation. The description correctly aligns with this by saying 'Get' (not modify). It adds a parameter default (max_results=20) and explains the instance parameter as optional, which supplements the schema. However, it does not disclose behavior like pagination limits, ordering, or which fields are returned beyond the output schema. Given the annotations cover the safety profile and the description provides minimal extra context, a 3 is appropriate.

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 and structured well: a clear one-line purpose followed by a compact argument list with inline explanations. It avoids redundant phrasing and front-loads the verb-resource clause. It could improve by adding usage context or a note on differences, but as a basic API description it is tight and readable.

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?

For a tool with three top-level parameters, a simple purpose, and an existing output schema, the description provides enough to understand the core operation: it retrieves change history with optionally limited results. The output schema is present, so return structure is not needed in the description. However, it falls short of explaining how to handle large histories (pagination) or any edge cases with issue_id formats, but these are minor given the schema and limited scope.

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?

Although the input schema has 0% description coverage, the description text itself explicitly explains each parameter: issue_id as Issue ID or URL, max_results as max activities (default 20), and instance as optional YouTrack instance. This provides more semantic detail than the raw schema, giving agents sense of what values to pass. The only missing semantic is perhaps format or constraints (e.g., max_results enforcement), but the core meaning is well covered.

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 clear action ('Get') on a specific resource ('change history of a YouTrack issue'). The verb-resource combination is specific. However, it does not explicitly distinguish this from sibling tools like get_issue_changes_summary or get_issue, though the 'history' wording implies a log of activities. The main gap is a lack of explicit differentiation, which prevents a score of 5.

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 provides no guidance on when to use this tool versus alternatives. It does not state any exclusion conditions (e.g., when to prefer get_issue_changes_summary for summaries) or mention any prerequisites. The only implicit signal is that it returns 'change history', but the user is left to infer the use case without explicit routing.

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