debug_traces

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the core behavior (recent vs. filtered search) and gives a hint about the tool's broader role ('Arch connects to live sessions...'). However, it does not disclose details like pagination, sorting, or whether results are limited to the current session, which would be useful for an agent.

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 (three sentences) and front-loaded with the core purpose. It avoids superfluous details and lists filters efficiently. The only minor waste is the initial '[Arch Debug]' prefix, which adds little value, but the overall structure is clear and compact.

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 no output schema and no annotations, the description covers the fundamental usage (recent vs. search) and lists all filterable fields. However, it does not explain the interaction between filters (e.g., whether sessionId narrows a search or acts only as a filter) or the output structure. For a tool with six optional parameters, this is adequate but leaves some ambiguity for an agent.

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 coverage is 100%, so each parameter already has a description. The description adds a key semantic distinction: the presence/absence of text, agentName, or hasError changes the operation mode. It does not go beyond this, but since the schema handles individual parameter definitions, a baseline of 3 is appropriate.

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 action ('Get and search trace events') and the resource ('trace events'), and lists the available filters (type, agent, text, error, session). It is specific enough to distinguish it from generic debug tools, though it does not explicitly name a sibling to contrast with.

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 conditional usage: with no search filters it returns recent events, with filters it searches stored events. This gives some context for when to apply each mode, but it does not mention when to prefer alternative tools like debug_get_errors or debug_session_history, nor does it state any exclusions.

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