exp_save

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

Annotations establish the safety profile (not read-only, idempotent, not destructive), and the description adds real value beyond them: recorded runs for that name are preserved and resume continues from where they stopped. This behavior about existing data is not derivable from the annotations or 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?

Two tight sentences with no padding, and the core action plus destination path are front-loaded. The resume clause is the only slightly tangential addition, but it is useful behavioral context rather than waste.

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 not be described, and the key persistence/resume behavior is covered. However, the unexplained `replace` parameter and the absence of any usage routing leave gaps for a spec-writing tool.

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 parameter burden. It clarifies that spec may be YAML or JSON, but says nothing about the `replace` boolean (default true) — whether it replaces the spec, the runs, or the directory, leaving a mutation-relevant flag undefined.

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 gives a specific verb (Save) and resource (experiment spec in YAML or JSON) plus the exact destination path <experiments_dir>/<name>/spec.yaml. It is clearly distinguishable from read/run siblings, though it does not name an alternative tool explicitly.

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 by the save/resume framing but there is no explicit when-to-use vs alternatives guidance (e.g. vs exp_template, exp_validate, or exp_run). The resume note hints at context but the agent must infer the selection conditions.

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