objc_dump

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

Annotations already declare a safe read-only, closed-world operation, and the description adds real value on top: it discloses that a local header file is returned, that the runtime backend reuses its existing session, that preview is opt-in and bounded, and it publishes concrete static-cache limits (5 minutes, 4 files, 16 MiB). It omits any notion of failure modes or what happens when both parameter sets are supplied.

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 dense sentences, zero filler, front-loaded with the core action and backend routing before the secondary facts about return value, preview bounds, and cache limits. Nothing repeats the annotations.

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 9-parameter tool with an output schema and safety annotations, the description covers the decisive behavioral facts: backend routing, session reuse, preview bounding, and cache constraints. The gap is coverage of arch, limit, and class_filter, which leaves an agent guessing on three of nine inputs.

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 carry parameter meaning and it only partly does: it explains binary_path, device_id, bundle_id, class_name, and backend selection, plus the opt-in nature of preview_chars. Three parameters (arch, limit, class_filter) receive no mention at all and are undocumented anywhere else.

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 and resource ("Dump headers") and immediately disambiguates its two operating modes: local binary_path via classdumpc, and live runtime via device_id/bundle_id/class_name. An agent can distinguish it from objc_query_instances purely from this text.

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?

Gives explicit condition-based routing (which parameter set selects which backend) and names the sibling to use for live values instead. It stops short of stating when the tool is inappropriate (e.g., non-ObjC targets, ambiguous parameter combinations), so it is clear but not fully exhaustive.

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