self_augment

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

Annotations already declare readOnlyHint=false and idempotentHint=false; the description adds real value by localizing the write to 'persist the chosen plan to issueops state.' That resolves what the non-read-only behavior actually is. It still does not say what happens to pre-existing state under the same state_key, nor whether repeated runs with cycles>1 mutate multiple keys.

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?

It is a single front-loaded sentence with no filler, but it is packed with three or four undefined internal terms ('scoring contract', 'candidate curriculum', 'Reflexion-style memory'), which costs comprehension. Tightening the jargon would raise this substantially without losing content.

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?

For a four-parameter, all-optional planning tool with no output schema, the description covers what it consumes (repo signals, research strategies) and what it can persist. The main gap is the absence of any statement about what the call returns — candidates, scores, or a plan object — which matters since no output schema exists to compensate.

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 100%, so all four parameters are already documented, and the baseline is 3. The description adds modest framing by linking 'persist the chosen plan to issueops state' to save_state/state_key and naming the purpose of the persisted plan ('durable Reflexion-style memory'), but it adds no format or interaction detail beyond the schema (e.g. how target_score relates to cycles).

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 uses a specific verb ('Plan') and resource ('the self-augmentation loop'), and lists the concrete outputs — feature/performance/quality improvements — so an agent can distinguish it from self_verify and self_augment_lesson. It loses a point for heavy reliance on internal jargon ('GENIUS_THINK.md', 'scoring contract', 'candidate curriculum') that an agent without repo context cannot decode.

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?

It draws one useful boundary: 'The native skill performs implementation; this tool exposes the scoring contract,' which tells the agent this is a planning-only call. However, it never names a sibling tool as the alternative (e.g. self_augment_lesson or self_verify_candidates), nor states when not to use it or what prerequisites exist before planning.

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