learnings_reject

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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds real value beyond that by disclosing the tombstone effect, implying the rejection is recorded persistently and the derivation won't resurface. It omits, however, that a confirmation prompt is involved (evidenced by the `yes` parameter) and what happens to the underlying candidate record.

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?

One clause, front-loaded with the action and zero filler. It is efficient, though arguably too sparse for a destructive operation with 23 parameters.

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?

This is an irreversible, destructive mutation inside a learnings loop, with 23 parameters and no output schema. The definition says nothing about reversibility, confirmation behavior, effect on the candidate store, or how it relates to learnings_confirm/candidates, leaving an agent without enough context to invoke it safely.

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 100% across 23 parameters, so the schema fully documents flags like `dry-run`, `no-input`, `idempotent` and `receipt`. The description adds nothing about the single required `id` (a candidate identifier) or which flags matter for a destructive one-shot call, so it sits at the schema-covered baseline.

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 ("Reject a candidate") plus a second effect ("tombstone its derivation signature"), which an agent can distinguish from learnings_confirm and learnings_forget by implication. It never names those siblings, and "derivation signature" is domain jargon left unexplained, so the differentiation is inferential rather than explicit.

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 when-to-use guidance, no mention of the alternative (learnings_confirm for acceptance), and no statement of prerequisites or irreversibility. With sibling tools learnings_candidates, learnings_confirm and learnings_forget all operating on the same objects, the agent is left to guess which one applies.

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