objc_query_instances

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

Annotations already declare a safe read, yet the description still adds substantial behavior: sensitive fields are redacted, snapshot_id pages never rescan the heap, Foundation strings/numbers/collections are bounded while other objects return leased references, and only ObjC-visible classes are reachable. That is exactly the extra context annotations cannot convey.

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 action is front-loaded and nearly every clause carries payload (redaction, defaults, paging, bounding). It is compressed to the point of being telegraphic — 'reuse/attach' and the run-on first sentence require re-reading — but there is little dead weight.

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 14-parameter tool with strong annotations and an output schema (so return values need no explanation), the description covers the important behavioral contours: redaction, bounding, snapshot paging, and per-call caps. The remaining gap is the discovery-vs-object_ids mode switch and the subclass/depth knobs, which an agent would have to guess at.

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 14 parameters, so the description must compensate and it only partly does: it explains field_names token trade-offs, snapshot_id paging, and the defaults behind max_fields (8 ivars), max_instances (20), and limit (10 per page). It leaves include_subclasses, max_depth, max_items, max_string_length, offset, and the object_ids/class_name mode interaction unexplained.

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 names a specific resource (allowlisted app ObjC instances) and the concrete actions: discover class instances, read mixed-class object_ids, then read bounded ivars. It distinguishes itself from getter/description-based approaches, though it never names a sibling tool such as objc_dump or debug_inspect, so an agent must infer the boundary itself.

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?

Usage is implied rather than stated: the 'discover class instances or read mixed-class object_ids' phrasing hints at two entry modes, and 'select field_names to minimize tokens' is practical guidance. But there is no explicit when-to-use-this-vs-objc_dump/debug_inspect rule and no exclusion conditions, leaving the agent to infer routing.

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