SimpleFunctions

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

No annotations provided, so description carries full burden. It discloses critical behavioral traits: state mutation ('Writes state'), asynchronous consumption timing ('consumed on the next evaluation cycle'), storage location ('Stored in the thesis signal log'), and authentication requirements ('Requires SF API key').

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 sentences, zero waste. Front-loaded with purpose ('Append...'), followed by behavioral mechanics and usage guidance, ending with requirements. Every sentence conveys distinct information (purpose, lifecycle/usage, prerequisites).

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 async mutation behavior, 100% schema coverage, and no output schema, the description is complete. It covers the full lifecycle (append → storage → consumption), auth, state implications, and sibling relationships without needing to describe return values.

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?

With 100% schema coverage, baseline is 3. The description adds valuable semantic context by providing concrete examples of signal content (news headline, user note, data point) that map to the 'content' parameter and type enum values, helping the agent understand what constitutes a valid observation beyond the schema's 'free-form natural language'.

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 specific verb 'Append' with clear resource 'thesis signal log' and provides concrete examples of content types (news headline, user note, data point). It effectively distinguishes itself from sibling trigger_evaluation by explicitly stating it does not trigger evaluation.

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?

Explicitly states when NOT to use for immediate results ('does NOT trigger evaluation by itself') and names the specific alternative sibling tool to call instead ('call trigger_evaluation afterward if you need an immediate update'). Clear prerequisites mentioned ('Requires SF API key').

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