self_reflect

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

The description says 'Save' and references 'Reflexion pattern' but goes no deeper into side effects — where the reflection is stored, whether it appends to memory_timeline, or whether repeated calls create duplicate entries. Annotations provide only readOnlyHint/destructiveHint/idempotentHint flags with no additional guidance, so the description carries most of the burden and only partially discharges it.

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?

Three short sentences, front-loaded with verb+resource ('Save a verbal self-reflection'). Negative guidance and content scope are packed efficiently without redundancy; every sentence earns its place.

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?

Covers the core essentials — what to save, when to call, what content belongs, what to avoid. Does not state where the reflection is stored (e.g., retrievable via memory_get or visible in memory_timeline) nor clarify the role of outcome/project/tags, leaving minor gaps for an agent operating within the rich sibling tool set. With no output schema, nothing about return values is owed.

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 covers only 2 of 5 parameters (reflection, task_summary); tags, outcome, and project have no schema description. The tool description's 'NOT for errors...' and 'meta-observations about strategy...' lines clarify the intended content of reflection, but the uncovered parameters remain unexplained, so the description only partially compensates for the 40% coverage 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 the verb ('Save'), the resource ('verbal self-reflection'), the pattern ('Reflexion pattern'), and the invocation trigger ('after completing a task or encountering difficulty'). The 'NOT for errors (use self_error_log)' line explicitly differentiates it from the closest sibling, making purpose unambiguous.

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?

Names the explicit alternative (self_error_log) and the condition that selects it ('NOT for errors'), plus the content scope ('meta-observations about strategy, approach effectiveness, process improvements') and trigger ('after completing a task or encountering difficulty'). The agent can decide without guessing.

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