Generate compact context strings for prompt injection from persistent memory, filtered by topic or agent and bounded by a token budget.
Generate compact context string for prompt injection
| Name | Required | Description | Default |
|---|---|---|---|
| focus | No | Optional topic focus | |
| agent_id | No | Optional agent filter | |
| max_tokens | No | Approximate token budget |
Changes observed during successful MCP inspections.
v0.1.0-alpha.29Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does not state what data source the context is drawn from, whether it is read-only, whether repeated calls mutate or consume memory, or what happens when the token budget is exceeded.
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 tight sentence with no filler, and the artifact and its purpose are front-loaded. It is appropriately sized but arguably under-specified rather than over-worded.
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 zero-required-parameter tool with no output schema, the description should explain the returned string's shape and the source of context. It conveys the output type but leaves provenance and budget behavior unexplained.
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%, so focus, agent_id, and max_tokens are already documented in the schema. The description adds nothing about semantics such as how the token budget is honored or what focus filtering actually selects.
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?
Clear verb (generate) plus specific artifact (compact context string) and intended use (prompt injection). It is distinguishable from hb_mem_store/hb_mem_query by producing a consumable string rather than storing or filtering records, though it never names those siblings.
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?
No guidance on when to call this versus hb_mem_query or hb_state_mem_get, nor any prerequisite (e.g., existing stored memories) or ordering advice. The agent must infer the trigger condition from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.