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

Annotations already establish readOnly/non-destructive/closed-world, so the bar is lower. The description still adds real behavioral value: it discloses that the tool reasons about which rows the VE and rf_korr calculations can consume and returns remediation advice per excluded row, and that the BIN supplies DME-specific lambda thresholds.

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 domain and action, followed by the report contents and the BIN caveat. Dense but every clause earns its place; no filler or restatement of the title.

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 no output schema, the description does the work of describing the return content (channels, usable-row counts, exclusion reasons with fixes). Together with full schema coverage on the nested file objects, an agent has enough to call it correctly; only the concrete output shape is left implicit.

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 baseline is 3, but the description adds meaning the schema does not: bin_file exists to source the DME's own lambda thresholds, and use_sample selects a practice BIN/drive rather than user files.

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 (read), resource (an MSS54HP drive log), and the exact output content: channels, usable-row counts for VE and rf_korr, and exclusion reasons. This is clearly distinguishable from sibling tools like read_bin, propose_ve, or about_matrix.

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?

Gives clear context for use (Testo or TUNER CSV drive logs) and explains the practice-mode alternative via use_sample ('before the owner has files'), plus when to attach the BIN. It stops short of explicit when-not-to-use guidance or routing against siblings like propose_ve.

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