inject_signal

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

Discloses that the tool writes state and stores data in the thesis signal log, consumed on the next evaluation cycle. However, it does not detail other potential side effects, concurrency behavior, or error conditions. With no annotations provided, the description carries the full burden, but it only partially fulfills 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?

Two sentences that are front-loaded with the primary action. Every sentence provides essential information without redundancy. Very efficient.

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?

Adequately covers purpose, usage, prerequisites, and behavior. Missing details on return value (no output schema) and error handling, but given the tool's simplicity and the presence of sibling guidance, it is nearly complete.

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?

The input schema already describes all parameters thoroughly (100% coverage). The description adds a brief classification of the content field as 'external observation (news headline, user note, data point)' and mentions the default type, but this is minimal added value beyond the schema.

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?

Clearly states the tool appends external observations like news headlines, user notes, or data points to a thesis. It distinguishes itself from the sibling trigger_evaluation by explicitly noting that this tool does not trigger evaluation, thus clarifying its specific role.

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?

Provides explicit guidance on when to use this tool and when to use a sibling tool, stating 'does NOT trigger evaluation by itself; call trigger_evaluation afterward if you need an immediate update.' Also mentions a prerequisite: '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.