Add a memory

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

Goes well beyond the annotations (destructiveHint, idempotentHint=false): it discloses secret scrubbing, the instruction/small-talk gate, duplicate detection that returns a 'duplicate_of' line, that Jev may correct the kind, and the exact semantics for retried dead ends. That is the kind of side-effect and failure-mode detail an agent cannot infer from the schema.

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 in the first sentence, and the long remainder largely earns its place with operational rules. It is a dense block rather than a structured list, which makes it heavier to parse, but there is little pure filler.

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?

Given a mutation tool with destructive/non-idempotent annotations, no output schema, and 0% schema description coverage, the description supplies the missing behavior: gate outcomes, refusal reasons, the duplicate_of return, and the automatic-recording caveat. Nothing essential to calling it correctly is absent.

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%, so the description carries the burden. It richly explains the 'dead-end' kind (what it means, what the line must contain, retry behavior) but says nothing about the other six enum values or the text constraints (3-500 chars, one line, scrubbing). Partial compensation, so a mid score.

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 concrete verb and resource ('Append one memory line to JEVMEM.md'), which is immediately distinguishable from the read-only siblings audit_memory, list_memory, and search_memory. The gate/scrub behavior further pins down what 'append' means here.

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?

Explicitly states when NOT to call it ('In Claude Code with jevmem's hooks... every turn is already recorded automatically: do not call this to repeat what the user just said') and when to call it ('only when the user asks you to record something the conversation itself does not state'). Refusal conditions for instructions/small talk and dead-end retries are also spelled out.

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