sync_memory_graph

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

With no annotations supplied, the description carries the full burden and does well: it discloses that the operation is both additive and destructive (removal of deleted files), and that a default guard blocks large removals and reports the anomaly instead. It does not describe the shape of that report or what happens to the graph if the sync is interrupted mid-run.

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 tight paragraphs with no filler, and the destructive-removal behavior plus the override warning are front-loaded. The phrase 'A sync keeps the graph and reports it' is slightly muddled about what is being reported, costing a point.

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-optional-parameter, no-output-schema tool, the definition covers what the sync does, the deletion side effect, and the safety override. Remaining gaps are minor: the nature of the anomaly report and whether repeated syncs are idempotent are unstated.

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% for the single optional parameter, so the description must compensate, and it does: allow_mass_removal is explained as an override for the mass-deletion guard, including the precondition (owner confirms the files really were deleted). It stops short of saying what the default false actually does on abort.

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 specific verbs and resources: ingesting unrepresented Markdown memories into the Graphiti graph, and removing entries whose source file was deleted. This is clearly distinguishable from the read/write memory siblings (search_memory, get_memory, remember). It does not explicitly name a sibling it complements, which keeps it just below 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?

The second paragraph implies usage context: a sync aborts/reports when the Markdown folder looks wrong (empty or many memories missing) and allow_mass_removal should be set only after the owner confirms deletions. That is real guidance on the risky case, but there is no statement of when to run a sync at all versus other memory tools, and no guidance on the normal, safe invocation path.

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