mkt_memory

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 usefully disclose three behavioral traits beyond the schema: the operation is read-only, it deliberately omits targets and content (privacy sanitization of output), and it forbids automatic replay of learned patterns. It still does not say what the response shape looks like or how results are ranked/windowed, which keeps it from a 5.

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 dense sentence with three clauses, front-loaded on the read-only nature and ending with the no-replay constraint; every clause carries information. It is compact to the point of terseness, but there is no wasted wording.

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?

There are no annotations, no output schema, and 0% parameter coverage, so the description is the only source of truth, yet it omits parameter meanings, return value characteristics, and sibling differentiation against mkt_experience and mkt_retro_analyze. For a tool whose whole value is knowing what it aggregates and what it withholds, this leaves significant gaps.

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% across three parameters, so the description must compensate and largely fails. It hints at 'channel' and at patterns derived from 'real operation receipts', but 'campaign' and especially 'minimum_confirmed' (default 3) — clearly a confirmation threshold gating pattern inclusion — are left completely undefined.

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 names a specific verb and resource: read-only aggregation of channel/action patterns derived from real operation receipts. That is concrete enough to distinguish it from generic tools, but nothing in the text separates it from close siblings such as mkt_experience, mkt_playbooks, or mkt_retro_analyze, so an agent cannot tell which memory-bearing tool to pick.

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 states constraints (read-only, sanitized, no auto-replay) but never says when to call this tool instead of the many siblings, nor any prerequisite such as needing prior confirmed operations. Usage must be inferred entirely from the phrase '运营经验'.

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