load_snapshot

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

With no annotations, the description carries the burden and does well: it discloses the asynchronous loading protocol (must poll before querying) and that comparison differences surface in hotspots and call trees of the analyzed run. It does not cover failure modes (bad path, unsupported file, large-file limits) or whether loading is idempotent, leaving a minor gap.

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?

Purpose is front-loaded in the first sentence, followed by the required follow-up workflow and then the comparison option. Dense but every clause carries actionable information with no filler.

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 two-param loader with no output schema, the description covers the purpose, the mandatory polling step, the retrieval tool, and comparison semantics. Only error/precondition behavior is absent, which is a modest gap for a tool whose output is consumed via query.

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 coverage is 100%, so both parameters are already documented. The description goes beyond the schema by explaining what baselineFilePath actually does behaviorally – differences are reported in the hotspots and call trees of the primary run, not the baseline. That adds real meaning.

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 (load), the resource (snapshot file), and enumerates the supported formats (.jps, .hprof, .jfr) with the goal (for analysis). This clearly separates it from siblings like query or check_status, which are downstream steps.

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 an explicit mandatory workflow: call check_status to poll progress and only retrieve data with query after 'data_ready'. It also describes the alternative comparison mode (set baselineFilePath) and when to use it. Both when-to-use and sequencing are spelled out.

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