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

Annotations confirm this is a non-read-only, non-idempotent, non-destructive write, and the description adds context annotations can't carry: a bounded per-caller/workspace memory pool and no API key requirement. It also warns against secrets/raw logs, which is genuine behavioral guidance. It doesn't cover what happens on pool exhaustion or whether repeats duplicate, keeping it at 4.

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?

The purpose and constraints are front-loaded, followed by a concrete call example. Three sentences and an example is slightly generous but each element (guidance, exclusion, example) earns its place.

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?

With an output schema present, the description need not explain returns, and it covers auth, capacity, exclusions, and an invocation example. It omits update/duplicate/idempotency behavior for a non-idempotent write, which is the remaining 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 100%, so the baseline is 3. The description adds value by mapping its four example categories onto the enum values (decision/preference/bugfix/discovery) and by tying the project param to later recall scoping, giving semantics beyond the raw schema text.

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 ("Persist") and resource ("durable memory") and enumerates what qualifies as a memory (architecture decision, preference, bug fix, discovery). It gestures at the sibling recall tool ("scope recall later") but never explicitly states how this differs from it, so it stops short of a 5.

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 gives clear positive context (durable items worth persisting) and a negative rule ("Do not store secrets or raw logs"), which is real when-not guidance. It stops short of explicitly naming the recall counterpart as the retrieval alternative, so it's a strong 4 rather than a 5.

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