sage_get_links

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

With no annotations, the description carries the full load. It explicitly states 'Read-only' and 'discloses only links between memories you can read', which are essential behavioral boundaries. It also specifies the filtering condition that both endpoints must be in the provided set, which is a precise behavioral trait. No rate limits or auth details, but these are not critical for this read-only tool.

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 tightly worded sentences, with the core purpose in the first sentence and all additional constraints (both endpoints, read-only, permission filter) stated without redundancy. No fluff, perfectly sized.

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 read-only tool with one parameter and no output schema, the description covers everything needed to use it correctly: what it returns, the filtering rule, the permission scope, and a typical use case. There are no gaps that would cause an agent to misuse it.

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 schema already describes the only parameter 'memory_ids' with the dual-endpoint condition, achieving 100% coverage. The description reinforces this condition and adds practical context by referencing 'the IDs a recall just returned' as a typical input source. This goes beyond mere schema repetition, so a score above the baseline 3 is warranted.

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 states a specific verb ('Read'), a clear resource (typed links among memories, part of the knowledge graph), and explicitly contrasts it with the write side. It also references typical input from 'a recall just returned', which distinguishes it from retrieval tools.

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?

The description provides a clear use case: 'Use it to reason over relationships: find what supersedes, contradicts, supports, or refines what among the memories you already have.' It also notes it is read-only and exposes only links the user can read, implying when not to use it (for writes). It does not explicitly name alternatives, but the read-side framing strongly suggests the write counterpart exists (e.g., sage_link).

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