suggest_managers

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

Annotations already provide read-only, idempotent, and non-destructive hints. The description adds transparency by disclosing the default file-writing side effect (managers.suggested.json) and explaining the write parameter's role in controlling persistence. It also explains the auto-exclusion of PMs, which affects output. No contradiction with annotations is present, since the write is a local output artifact, not a mutation of the YouTrack system.

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 well-structured. It opens with a one-sentence summary, adds a brief algorithmic explanation, and then lists parameters in a clean Args block. Every sentence adds value; there is no redundancy, and the structure makes scanning easy.

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 that all parameters are optional with defaults, an output schema exists, and annotations cover safety, the description is nearly complete. It covers the algorithm, parameter semantics, and output side-effects. Minor gaps include not stating permission requirements for reading all accessible projects, the potential performance impact of large lookback windows, or behavior when no candidates are found. These are not critical for a competent agent calling the tool.

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?

The schema provides no parameter descriptions (0% coverage), so the description is the sole source of semantics. It clearly explains all four parameters: lookback_days as activity window, projects as comma-separated shortnames with empty meaning all accessible, write as whether to persist or just print, and instance as optional YouTrack instance. This fully 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 states a precise function with a clear verb and resource: 'Bootstrap a manager mapping from recent YouTrack activity.' It also breaks down the heuristic approach (detecting PMs, scoring remaining candidates), making the purpose unambiguous. No sibling tool offers this exact capability, so it is well differentiated.

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 implies the tool is used when manager mappings need to be inferred from activity data, but it never explicitly says when to use it or when to avoid it. There is no mention of alternative tools (e.g., get_team_dashboard) or exclusions for cases where manager data is already available. Usage context is left to inference.

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