memory_enrich_knowledge

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

With no annotations, the description carries the full burden for a write tool and omits the core behaviors: what merge_mode actually does, whether existing knowledge is overwritten or appended, idempotency, and what happens when entity_path does not resolve. It does disclose the output-formatting convention (high-density English for specs, Indonesian slang for aliases), which is real value, but write semantics remain undisclosed.

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?

Front-loaded with the action, then the two formatting mandates, with no filler sentences. Slightly repetitive in the doubled 'MANDATORY:' prefix, but efficient overall.

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 12-parameter mutation tool with zero schema coverage and no annotations, the definition is under-specified: merge semantics, the required path's expected form, and symbol scoping are all absent. The output schema removes the need to explain return values, but that alone does not close the gap.

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 coverage is 0%, so the description must compensate. It names eight of twelve parameters (purpose, logic_phases, upstream, downstream, guardrails, side_effects, error_handling, colloquial_aliases) and gives a content convention for two of them, but never explains entity_path, symbol_name, merge_mode, or child_summary — including the only required parameter.

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 a specific verb ('Save deep understanding') and resource ('a file/folder or function/symbol'), which is enough to separate it from the read-oriented siblings (inspect, find_by_intent, get_phase_map). It stops short of naming the write counterpart (memory_sync_codebase), so the boundary with auto-generation is not drawn.

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 description spends its words on mandatory content formatting, not on when to call this versus memory_sync_codebase or the inspection tools. There is no stated trigger, no prerequisite (e.g. entity must exist in the index), and no exclusion criteria.

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