exp_report

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

Annotations already declare the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description goes beyond them by disclosing the two files written, that 'interpretation= saves a new one' with an author attribution scheme, and that firmware_check triggers proj_vs_runtime as a side effect. The audit-log content also signals that writes are tracked. Missing only details like overwrite behavior for existing reports.

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 verb and target paths are front-loaded, which is good, but the body is a long run-on list that conflates artifact sections with parameter behavior. Every clause carries information, yet the density could be structured more readably.

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?

An output schema exists, so return values need no explanation, and the description covers the substantive behavior an agent needs: what files are produced, that the interpretation is stored separately and labelled as not computed, and the firmware_check side effect. The unexplained fmt parameter and the lack of explicit alternative-tool routing are the remaining gaps.

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. It explains interpretation (saves a new one; author=agent|operator|<name>), author, and firmware_check, but never mentions what fmt='both' controls and only implies that name is the experiment directory. Two of five parameters remain unexplained, so it adds real but incomplete value.

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 opens with a specific verb+resource: 'Write <experiments_dir>/<name>/report.md and report.html', so the agent knows it produces report artifacts for a named experiment. It enumerates the artifact contents (identity, criteria table, metrics, charts, run table, spec, audit log, interpretation), which further distinguishes it from siblings like exp_evaluate or exp_compare that analyze rather than render. It stops short of explicitly naming a sibling contrast, so a 4 rather than 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?

Usage is implied rather than stated: after a run, this is the tool that emits the report. The description does give conditional behavior ('firmware_check=true runs proj_vs_runtime first'), which hints at when the extra check matters, but there is no explicit guidance on when to prefer exp_report over exp_evaluate, exp_compare, or exp_get.

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