symbol_lookup

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

With no annotations, the description carries the full burden and does well: it discloses the sparse-.map failure mode that yields 'fake function names', states that it emits an explicit warning and offers a replacement source, and guarantees a hard 'not found' rather than guessed names. It omits permission/rate-limit or performance characteristics, but for a pure lookup the disclosed edge-case behavior is meaningful.

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 core purpose and routing advice are front-loaded, and the ★ markers separate the operational guidance from the failure-mode caveats. It is somewhat long and re-states the sparse-map problem across several lines, but nearly every sentence carries actionable information for this tool's tricky failure modes.

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-value explanation is not required, and the description instead covers the input requirements, the sparse-map edge case, and error semantics. For a 2-parameter tool with an output schema this is close to complete; only address-format specificity is missing.

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 compensate. The inline example symbol_lookup("build/app.elf", ["0x08004a2c"]) clarifies that `path` is a firmware artifact and `addresses` is a list of hex address strings, which adds real value. However, it never specifies accepted path variants or address string formats ('0x' prefix required? decimal allowed?), leaving notable gaps.

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 first line states a specific verb+resource+transform: reverse-lookup an address into 'function name + offset', and the following line frames it as the key step in fault-to-code localization. This clearly distinguishes it from siblings like parse_map, decode_fault and stack_unwind, which the agent can tell apart without opening schemas.

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 strong conditional guidance: prefer .elf over .map, and explains the reason (real st_size in .symtab enables in-function checks). It also tells the agent the tool will surface a same-directory .elf when a sparse map is detected. It does not explicitly name sibling alternatives (e.g., parse_map), so it falls short of a 5.

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