Metis — Get Agent Runs

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

Since no annotations provided, description carries full burden. Clearly indicates read-only behavior (retrieve, returns log). Describes output format and ordering (newest first). Lacks explicit safety or authorization notes, but for a get tool the behavior is transparent enough.

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?

Concise and well-structured. First sentence states purpose, second explains what it returns, third gives relationship to log_agent_run, then bullet-style args. No redundant sentences.

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?

Covers key aspects: what it does, parameters, return format (text block with fields). Output schema exists but description still lists fields. Could mention pagination or error cases, but for a simple retrieval it is sufficiently complete.

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?

Input schema provides only titles and defaults (0% coverage), but description includes an 'Args' section explaining each parameter in detail: limit (max count, default 10), since (ISO date/datetime, empty for all), agent_slug (filter by slug, empty for all). This adds significant meaning beyond schema.

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?

Clearly states it retrieves recent agent run history from the database. Uses specific verb 'Retrieve' and resource 'agent run history'. Distinguishes from sibling tools like log_agent_run (write) and other get_* tools by focusing on runs and specifying results order.

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?

Mentions usage 'for the dashboard or for reviewing recent activity' but does not explicitly state when not to use or compare with alternative tools. No exclusion criteria or guidance on selecting this over similar tools like search_memory or list_recent_sessions.

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