memory_add

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

Annotations already declare readOnlyHint=false and destructiveHint=false, and the description adds genuinely new behavior: content is written as Markdown files and secrets (tokens, keys, passwords) are redacted before writing. That redaction note is important context an agent cannot get from structured fields. It stops short of covering duplicate behavior, which matters given idempotentHint=false.

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?

Two tight sentences, the core action front-loaded and the safety-relevant redaction detail second. Nothing is redundant.

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?

An output schema exists, so return-shape explanation is not required, and the annotations plus a fully described schema carry most of the load for an 11-parameter mutation. The remaining gap is where memories land (the project parameter's storage semantics) and how duplicates or re-adds are handled given non-idempotency.

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 100% with per-field descriptions for all 11 parameters, including the 'type' values (lesson/do/dont/history) and link syntax. The description adds nothing about parameters, which is acceptable at full coverage but leaves it at the baseline.

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 states a specific verb and resource ('Save a memory as Markdown') plus the observable outcome ('return the file path'). It is clearly a write counterpart to the sibling search/related tools, though it never names them to draw the boundary explicitly.

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 guidance on when to add a memory versus when to search first with memory_search, nor on what qualifies as worth persisting. An agent must infer the whole usage context 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.