octave_eject

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

With no annotations, the description carries the full burden. It discloses template generation when content is null, flexible section matching, and silent omission of non-existent sections. However, it does not state whether the tool modifies any state (e.g., it appears to be a pure transformation), nor does it describe error handling, rate limits, or authorization requirements. The behavioral disclosures are adequate but incomplete.

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 sentences clearly convey the core functionality. The first sentence is front-loaded with the primary action. The second adds key details (modes, formats, template generation). No redundant or extraneous information. Very concise while still informative.

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?

Given the tool's complexity (5 parameters, 2 with enums, no output schema), the description covers the main behaviors: projection modes, output formats, template generation, and special section handling. It does not specify validation behavior or side effects, but the core use case for an eject/export tool is well-covered. The omission of return value format is partly mitigated by the absence of an output schema.

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 parameters are already documented. The description adds meaning by explaining the effect of each mode (e.g., executive yields STATUS,RISKS,DECISIONS), and the flexible section input (e.g., '§3', '3', '§3::CAPABILITIES'). This goes beyond the schema's enum labels and type descriptions, providing actionable context for choosing parameter values.

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 clearly states the action ('eject OCTAVE content'), the resource ('OCTAVE content'), and the modalities ('projection modes', 'canonical, authoring, executive, and developer views'). It also lists output formats and template generation capability. The tool is distinct from sibling tools (compile, validate, write) because it focuses on exporting/transforming content in different views and formats.

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?

No explicit guidance on when to use this tool versus siblings (e.g., octave_validate, octave_write). The description does not mention prerequisites, typical use cases, or conditions that would make this tool preferable. An agent would have to infer usage from the tool name and behavior alone.

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