Metis · Data Analyst — Data Memory Scan

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

With no annotations, the description carries the full burden and does so well: it discloses which file types are read (.R/.Rmd/.qmd plus CLAUDE.md/README), which directories are skipped (History/, r_libs/, renv/, '- Copy', _to_delete), that unchanged scripts are not re-read, and that force overrides the incremental behavior. What it does not cover is where the learned memory is persisted or any permission/auth requirements.

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 opening line front-loads purpose, followed by behavioral constraints, then a compact args block. No filler sentences. The args block is slightly repetitive of schema field names but is justified given 0% schema description coverage.

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?

Return values need not be explained because an output schema exists, and the behavioral rules for a multi-parameter scan tool are well covered. Missing only secondary details such as persistence location and whether re-scans merge or replace prior memory.

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 must compensate, and it does: folder is documented with a required path format (C:/… or /mnt/c/…) and the empty-string semantics, force is defined as re-read-even-if-unchanged, and label/project_id are identified as optional. It adds real meaning beyond the bare titles and defaults in the schema.

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 specific verbs and resource: learn a folder of analysis scripts, or refresh all known folders. It is clear what the tool ingests and at what granularity. It does not name a sibling (e.g. data_memory_script, scan_project_scripts) to differentiate itself explicitly, so it stops short of 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?

"With no folder, every registered folder is refreshed" implicitly signals the two modes (targeted scan vs. global refresh). However, there is no guidance on when to use this versus adjacent tools like data_memory_script, data_memory_status, or scan_project_scripts, leaving the agent to infer.

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