get_agent_runs

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

No annotations are provided, so the description carries full burden. It clearly states the operation is read-only ('Retrieve'), explains the ordering ('newest first'), and describes the output format. It does not mention side effects or destructive behavior, which is appropriate for a retrieval tool. The behavioral context is well-covered.

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 well-structured: a concise one-sentence summary followed by a brief paragraph, then structured 'Args' and 'Returns' sections. Every sentence provides value, no fluff. It is front-loaded with the purpose and remains 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?

The description fully covers the tool's purpose, parameters, return format, and data source ('written by log_agent_run'). With an output schema present, the description explains the return fields. No gaps remain for a simple retrieval 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 input schema has 0% description coverage, but the tool description includes a detailed 'Args' section explaining each parameter: limit (max runs, default 10), since (ISO date/datetime, empty defaults to all dates), and agent_slug (filter by slug, empty returns all). This adds significant value beyond the bare 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?

The description starts with 'Retrieve recent agent run history from the database,' specifying the verb 'retrieve' and the resource 'agent run history.' It further details that it returns logs of past agent work (what ran, when, status, token usage) ordered newest first, clearly distinguishing it from siblings like 'get_agent_context' or 'get_tasks'.

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 states it's 'for the dashboard or for reviewing recent activity,' providing a clear usage context. It also notes that these rows are written by 'log_agent_run,' giving background on data source. However, it does not explicitly warn against using this tool for other purposes or compare it to alternatives like search tools.

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