memory_exploration_record

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false; the description adds real value beyond them by disclosing path-resolution rules (relative to root, outside-root refused), the 64-file/32 MB caps, and the replace-on-repeat semantics that explain the idempotent behavior. Missing only what the stored record returns or how failures surface.

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?

Four sentences, each earning its place: purpose, trigger, path/limit constraints, and replacement semantics. Front-loaded with what the tool does before the caveats.

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 and full schema coverage, the description supplies the missing behavioral context: trigger condition, path refusal, size limits, and overwrite semantics. Only the post-write response shape is left implicit, which is minor given the operation's nature.

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 100%, so the schema already documents root, files, project, question, and conclusion. The description adds only the 32 MB per-file limit (not in schema) and the outside-root refusal rule; the 64-file cap merely restates maxItems. Baseline 3 is appropriate.

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 specific verb and resource — recording an exploration conclusion plus SHA-256 hashes of every file read — which is unmistakably distinct from siblings like memory_exploration_recall or memory_save. The agent knows exactly what artifact this produces.

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 says to call it 'after answering a structural question by reading files (how X is wired, where Y is decided)', which is a clear triggering condition. It does not name the complementary recall tool or state when NOT to use it, so it falls short of the 5 tier.

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