import_memory

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=false), the description discloses crucial behavior: content lands in a review queue and is not saved as a record until the user approves, and secret-like lines are skipped rather than stored. These are non-obvious safety traits an agent must know before calling.

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 core action and its queue semantics, then format details, then the secrets caveat. It is dense and information-rich, though the parenthetical clauses stack up slightly, making it a bit packed rather than crisp.

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 write tool with no output schema, the description covers the key outcome (items become review entries pending approval) and the secret-skipping behavior. It does not describe the shape of the response or how many items may be produced, a minor gap given the absence of an output schema.

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 already 83%, and the description adds meaning: it explains what format=memory and format=flowstate_markdown each ingest, that 'text' should carry the file contents, and that project is required for every write. It adds real value over the enum lists but doesn't touch every parameter (e.g. model/source nuance).

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 opens with a specific verb and resource ('Bring memories or notes into a project's REVIEW QUEUE') and immediately clarifies the write semantics and that nothing is persisted until approval. This clearly distinguishes it from direct-write siblings like log_learning or create_component by routing content through a review queue.

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?

It explains the two format modes and when each applies (format=memory for Claude/ChatGPT exports vs format=flowstate_markdown for `flowstate export-md` files). However, it never explicitly names an alternative tool or states when NOT to use this import path versus logging directly.

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