mat_threads

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

With no annotations, the description must carry the behavioral load. It does disclose the return shape of list mode and the hierarchical drill-down order (threads → frames → locals), which is valuable, but says nothing about cost (MAT report parsing is expensive), prerequisites (report must be loaded/open), or whether repeated calls across reports are expected.

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?

A single front-loaded sentence that moves from the default listing to progressive drill-down, so the common case is stated first. The full bilingual duplication doubles the length without adding information, which keeps it from a 5.

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 values need not be explained, and mode selection is covered. However, it omits that report_id refers to a previously opened heap dump managed by siblings (open_heapdump/list_heapdumps), which is the main thing an agent could get wrong before calling.

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, and it does for two of three parameters: it clarifies thread is an id string and frame is an index, and that frame is only meaningful together with thread. report_id is left to the schema's title alone, which is a minor but real gap.

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 ('List threads') and enumerates the fields returned (name/state/daemon/frameCount), plus the two drill-down modes. It does not name the closely related siblings (mat_threadlocals, mat_sql_in_threads, mat_object), so the agent must infer differentiation from mode semantics alone.

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 made conditional in a usable way: pass thread=id to get stack frames, then additionally pass frame=idx to get frame locals. That is a clear when-to-use signal for each mode, but there is no guidance on when to prefer mat_threadlocals or mat_sql_in_threads, and no exclusions.

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