crosspad_trace

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

Annotations provide only readOnlyHint=false and destructiveHint=false, so the description carries full burden. It discloses key behaviors: non-halting RAM polling, background trace lifecycle, safe vs risky actions ('cheap; safe for the LLM' for read), soft-fail behavior for SWV init, blocked flash regions for writes, core halting for call, and config persistence location. This is exceptionally transparent.

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 long (a dense bulleted list) but every line is functional. It's well-structured with action → behavior mapping and front-loads the most important instruction (run doctor FIRST). No fluff or filler. The length is justified given the 14 distinct actions and their differing param requirements, but a more compact reference table could have served equally well.

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?

Despite 17 params and an output schema, the description is remarkably complete: it maps actions to required params, explains lifecycle (config_set → start → add/remove → status → read → save), discloses experimental paths, documents fallback/soft-fail behaviors, and covers edge cases like raw address bypass and type decoding. For a hardware tracing tool with this complexity, the description is thorough and self-sufficient.

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 the baseline is 3. However, the description adds substantial value beyond the schema: the action field's description enumerates required params per action, and tools like signals and writes explain raw @address syntax, type decoding, and allowlist/blocklist regions. The call action disambiguates AAPCS, confirm requirement, and default ret types. The description meaningfully supplements the 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 gives a specific verb+resource: 'Real-time SWD tracer for the STM32G0B1 firmware (ST-Link)' with a clear enumeration of all 13 actions and what each does. It clearly distinguishes itself from siblings like crosspad_run (execution control) and crosspad_log (log access), being specifically about hardware trace/polling. The STM-specific scope makes it unmistakable.

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 explicit sequencing guidance ('run this FIRST; resolve issues, then config_set'), and defines when each action applies. It notes deprecated/experimental features (swo UNTESTED, write/call requiring confirm). However, it doesn't explicitly state when to prefer this tool over siblings like crosspad_search_symbols or crosspad_stats, though the domain distinction (hardware trace vs. build/test) is implied.

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