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

No annotations exist, so the description carries the full burden. It usefully discloses the consequence ('tombstone') and the cascade effect on related data ('derivatives become stale_derived'), which is real behavioral value. However, it says nothing about reversibility, required permissions, or whether the original payload is retained.

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?

A single compact clause with the verb and the two consequences front-loaded; nothing is wasted or buried.

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?

The tool is simple and the description covers the core outcome and downstream effect, which is the most important thing for an agent to know. But with no annotations, no output schema, and two undocumented parameters, an agent still lacks detail on argument shape and error/auth behavior.

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 only 33% — 'id' and 'project' have no descriptions at all — and the description adds no meaning about what these identifiers are or their format. Only 'by_operator' is documented, and that documentation lives in the schema, not the description.

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 ('Retract') and resource ('a memory') plus the resulting state ('tombstone'), which is clearly distinct from siblings like memory_write or memory_resolve. It doesn't explicitly name an alternative, but an agent can differentiate it by verb alone.

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 retract versus resolve or overwrite, no mention of irreversibility, confirmation, or prerequisites. Usage is only implied by the verb itself.

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