Narya Start

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 error behavior (stops at first error via error_at/messages), latency (first heavy import is slow, subsequent commands fast), and an automatic fallback (source_only used when compiled imports trigger an anomaly). It also states the return payload.

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-loads the core action and return values in the first sentence, then adds per-mode behavior. The single dense paragraph is information-rich, though its length and multi-clause sentences slightly reduce scannability.

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 restated, yet the description explains them anyway and covers load semantics, import fallback, and error stops. It omits any mention of the session lifecycle/cleanup implied by the narya_close sibling and the timeout parameter.

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 0%, so the description must compensate, and it covers five of six parameters meaningfully: file, line, imports (with path semantics relative to `directory` or the file's directory), directory, and source_only. The `timeout` parameter is never explained, leaving one gap.

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 ("Start") and resource ("an interactive session (a live Narya process)") and names what it returns (session_id, open holes). It hints at its role relative to narya_exec/narya_synth but never explicitly contrasts itself with the many sibling check/audit/session tools, so an agent must infer the boundary.

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 concrete condition-based guidance: with `file` it loads command-by-command to `line`; with `imports` it imports first; without a file it yields a scratch session for narya_exec / narya_synth. That names alternatives and the conditions that select them, but offers no explicit "when not to use this" or comparison against narya_try / narya_check.

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