memory_graph_purge

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

With no annotations, the description carries the full burden and does useful work: it discloses the operation is physically destructive, enumerates what is preserved (sessions, observations, memories, lessons), and describes two refusal behaviors for partial/oversized snapshots. It doesn't cover permissions, irreversibility mechanics, or response shape, so it falls short of 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?

Two dense sentences that are front-loaded with the destructive action followed by preservation and refusal semantics. Efficient and mostly waste-free, though the phrasing is slightly compressed.

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 4-param destructive tool with no output schema and no annotations, the description covers what is deleted, what survives, the inventory precondition, and refusal limits. Missing only peripheral details such as permission requirements or return values, which the schema partially implies.

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% and each parameter is self-documented in the schema (audit reason, exact edge/node inventory, project id). The description adds no syntax or format detail beyond that, so the baseline 3 applies.

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?

The description gives a specific verb ('Physically delete') and a well-scoped resource ('one explicit project's complete bounded live graph'), which clearly separates it from read-oriented siblings like memory_graph_query. It stops short of naming a sibling alternative, so it earns a solid 4 rather than a 5.

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?

It implies the precondition ('after an exact node/edge inventory') and states refusal conditions ('refuses partial or oversized snapshots'), which is more than nothing. But it never states when to choose this over e.g. memory_graph_upsert or memory_governance_delete, so usage guidance is only implied.

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