memory_recall_compact

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

Annotations already establish readOnlyHint, idempotentHint, destructiveHint=false and a closed-world scope, so the safety profile is covered. The description contributes the genuine behavioral fact that output is a single deduplicated packet with no repeated items or context, but says nothing about how token_budget truncates results or what the packet contains.

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?

It is a single front-loaded sentence with no filler, which is structurally clean. However, its brevity comes from unexplained jargon rather than economy, so it reads as under-specified rather than tight.

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?

A five-parameter, zero-coverage tool with no output schema and no parameter documentation needs a description that explains inputs and return shape; this one provides neither. An agent would have to guess at every argument and at what an SMC/1 packet is.

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?

All five parameters (query, scopes, session_id, project_root, token_budget) have 0% schema description coverage, so the description carries the full burden of explaining them and explains none. The phrase "single SMC/1 packet" gives no clue about scoping, session targeting, or how token_budget bounds the result.

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 says it "Return[s] a single SMC/1 packet", which names a verb and an output artifact but never states that this is a memory recall operation or what SMC/1 means. The sibling memory_recall is not mentioned or differentiated, so an agent cannot tell which of the two to pick from the text 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 when-to-use guidance, no prerequisites, and no reference to alternatives such as memory_recall despite that sibling clearly overlapping in purpose. The only implicit hint is the "compact" name, which the description does not reinforce.

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