memory_reject

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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds the important detail of what exactly is destroyed (the staging row) and what is not affected (no memory is written). It omits idempotency behavior on repeat rejection, keeping it short of a 5.

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?

Three tight sentences with zero filler; the core action and its non-commitment guarantee are front-loaded before the usage 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?

For a one-param destructive tool with no output schema, the description covers action, effect on storage, and selection guidance. It lacks only error/permission behavior (e.g., rejecting a non-pending id), which is a minor gap.

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?

Single parameter with 100% schema description coverage ('Proposal id (from memory_proposals)'), so the schema already carries the semantics. The description adds no syntax or sourcing detail beyond that, matching the baseline for full coverage.

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 ('Discard a pending proposal') and immediately scopes the effect ('Deletes the staging row; no memory is written'). An agent can distinguish this from memory_propose/memory_ratify purely on the 'without committing it' framing.

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?

'Use this for drafts that should not become canon' gives a clear selection condition for when to reject rather than ratify. It stops short of naming memory_ratify (or memory_prune/forget) as the explicit alternative, so the routing is implied rather than stated.

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