rad_get_stack

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so safety is covered. The description adds the meaningful detail that at most 128 backend frames are returned, which constrains expectations, but says nothing about pagination behavior or ordering.

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?

Two sentences, front-loaded with the core action and zero filler. Every clause carries information.

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?

An output schema exists, so return values needn't be described. However, with three undocumented parameters and an unstated session/thread prerequisite, an agent lacks enough to call it correctly without inspecting the schema.

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 description coverage is 0%, so the description must define 'count', 'start', and 'session_id'. It explains none of them; 'at most 128 backend frames' vaguely hints at a cap on 'count' but never clarifies 'start' as a pagination offset or that 'session_id' identifies the debugging session.

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?

States a specific verb (read) and resource (native call stack with symbol names and source locations), plus a hard cap of 128 backend frames. It doesn't explicitly differentiate from siblings like rad_get_state or rad_evaluate, but 'call stack' is distinct enough to route an agent.

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?

'Selected thread' implies a prerequisite (a context must be selected, likely via rad_select_context) but this is never stated explicitly. No when-to-use/when-not guidance or alternatives are named, so usage is only implied.

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