save_pattern

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

No annotations exist, so the description carries full load, and it does well: idempotent upsert semantics by pattern id, an existing timestamp is never rewritten, and the server stamps discovered_at when absent when writing to Qdrant. Missing are failure modes, permission/auth requirements, and whether the write is atomic or rate-limited.

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?

The first sentence is front-loaded and useful. The middle sentence justifying the SavedPattern-vs-Pattern return-type naming is design rationale that does not help an agent select or invoke the tool, so it dilutes an otherwise tight definition.

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?

With an output schema present, return values need not be described, and the description covers write semantics, idempotency, timestamp handling, and the Qdrant dependency. What remains missing for a mutation tool with zero annotations is error/permission 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?

Reported schema description coverage is 0%, though the nested $defs actually document most fields, so the description's obligations are lighter than the metric suggests. The description echoes the id-overwrite and discovered_at-stamping semantics already present in the schema rather than adding new parameter meaning, landing at the baseline 3.

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 opening sentence gives a specific verb and resource ('Store one pattern') plus the post-condition ('return it as written, with discovered_at filled in'). It is distinguishable from siblings like find_patterns and query_qdrant by the write/read split, though it never names an alternative explicitly.

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?

Usage is only implied — the tool stores a single pattern, and re-saving the same id overwrites. There is no stated when-to-use versus find_patterns, no when-not, and no guidance on when saving is appropriate for an agent. 'Needs Qdrant only' is a useful dependency note but not usage routing.

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