keil_start_debug

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

With zero annotations, the description carries the full burden and does disclose the key behavioral trait: the operation 'May halt MCU', which explains the mandatory confirm=true human-authorization gate. That is meaningful side-effect disclosure that an agent could not infer from the schema. It stops short of describing failure modes, whether an existing session is replaced, or what happens if a probe is already attached.

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?

Three short sentences, no filler, and the most consequential facts (backend scope and the MCU-halt warning) are front-loaded. The trailing whitespace and slightly compressed phrasing around the ELF default cost it a perfect score but nothing is wasted.

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?

For a session-mutating tool with an output schema present, the description covers the critical safety gate, the backend scope, and the ELF default, which is enough to call it correctly. The remaining gap is the undocumented target/probe_id/project_path parameters and the unclear required/optional status of target_override.

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% across 7 parameters, so the description must compensate and only partly does: it explains target_override, elf_path ('defaults to the selected project's output'), confirm, and the backend pairing with pyOCD/ST-Link. It says nothing about target, probe_id, or project_path, leaving three parameters entirely undocumented in both schema and description. It also asserts 'target_override is required' while the schema marks no parameters required, an inconsistency that further muddies parameter semantics.

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 opens with a concrete verb-plus-resource ('Connect pyOCD/ST-Link') and immediately scopes it against the alternate backend ('NOT native µVision'), so an agent knows this starts a debug session over an external probe, not µVision's native debugger. It does not name any sibling tool such as keil_flash or keil_diagnose_connection, so differentiation from the rest of the toolset is only partial.

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?

It gives a hard precondition ('requires human-authorized confirm=true') and an exclusion ('NOT native µVision'), which is real when-to-use guidance. However, it never says when to prefer this over keil_flash, keil_diagnose_connection, or keil_get_status, and it gives no guidance on ordering relative to build/flash, so the alternative selection is left to inference.

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