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

Annotations already cover idempotency and non-destructiveness, so the description adds real value by disclosing what gets written ("cited lessons and up to five experimental briefs in the shared brain") and the blast-radius boundary ("never publishes or promises performance"). Remaining gaps are around failure modes with exhausted credits/USD or what "bounded" costs in practice. Restating "Idempotent" duplicates the annotation rather than adding nuance.

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 dense sentences with the core action, side effect, and safety boundary front-loaded; no filler. One small inefficiency: "Idempotent" repeats the annotation, and "bounded" / "shared brain" are unexplained jargon that could have been traded for a missing parameter hint.

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?

Placeholder.

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 12 required parameters, so the description carries the full burden and only touches four: quoteId ("reviewed learning quote"), maxUsd/maxCredits ("approved credits/USD cap"), and maxVariations ("up to five"). seriesId, goal, from/to, language, expectedEvidence, idempotencyKey and workspaceId receive no explanation anywhere, and opaque fields like the sha256 expectedEvidence pattern are especially costly to leave undocumented.

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 action ("Start one bounded model call") and its concrete inputs/outputs (reviewed learning quote, cited lessons, up to five experimental briefs), which goes well beyond the vague title. It implicitly points at the learning_quote sibling by requiring a "reviewed learning quote," but never names learning_quote/learning_get/learning_control, so an agent must infer the ordering of the family. Clear on what it does, weaker on distinguishing it from siblings.

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?

"from a reviewed learning quote and approved credits/USD cap" implies prerequisites (a prior learning_quote, an approved budget) but never states them as preconditions. There is no explicit when-to-use vs alternatives, no mention of following up with learning_get or stopping via learning_control. Usage is inferable but not spelled out.

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