get_recap

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds only the HTTP path, which conveys nothing behavioral beyond what the annotations state — no indication of what a "recap" contains, whether it is cached/aggregated, or whether it requires auth.

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?

Two very short lines, front-loaded and free of padding. The endpoint line is thin on value but does not bloat the definition and is arguably the only concrete anchor provided.

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?

With no output schema and no explanation of what the recap returns, a 0-param read tool still needs the description to say what data comes back and how it differs from the many other stats endpoints in the sibling list. That gap leaves the agent unable to select this tool confidently.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a parameterless tool is 4. No schema information is lost.

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?

"Get Recap" essentially restates the tool name; the only added information is the raw endpoint GET /api/system/stats/recap, which hints at a system-stats domain but does not state a specific verb+resource in agent-readable terms. It gives no signal that distinguishes it from siblings such as get_stats, get_status, or get_stats_digest.

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?

There is no guidance on when to call this tool, what scenario it fits, or which alternative siblings (get_stats, get_stats_digest, get_http_stats, get_bandwidth_stats) it should be preferred over. The agent is left to guess entirely.

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