memory.linked_prs

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. However, the description only states the function without any behavioral traits—such as whether results are paginated, what the default sort order is, whether it only returns active PRs, or any rate limits/permission requirements. For a tool with no annotations, this leaves significant behavioral gaps for the AI agent.

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?

The description is extremely concise at one short sentence (5 words in Portuguese) with zero wasted words. It is front-loaded with the primary action. However, given the lack of annotations and behavioral context, a slightly more informative description could have been equally concise while providing more value, such as adding 'Returns a list of PR IDs or full objects'.

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?

Considering the context: 1 required parameter, no parameter docs, an output schema exists but its content is unknown, and there are many sibling tools. The description defines the core 'what' but lacks completeness for an AI agent to confidently invoke it. The output schema may provide return value structure, but the description doesn't hint at whether results are limited, ordered, or filtered. For a simple list tool with good context signals, a score of 3 reflects that the description is minimally viable but leaves the agent guessing about return format and behavior.

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 schema description coverage at 0%, the description must add meaning beyond the parameter name 'memory_id'. The description does clarify that the input is a MemoryItem ID (since the resource is 'PRs linkados a um MemoryItem'), which is helpful but minimal. The schema already makes 'memory_id' required, so the description only reinforces the parameter's purpose without adding format, example, or context about where to obtain the ID. Baseline 3 is appropriate as the description does not fully compensate for the lack of schema documentation.

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 clearly states the verb 'Lista' (List) and the resource 'PRs linkados a um MemoryItem' (PRs linked to a MemoryItem). It effectively distinguishes from sibling tools like 'memory.pr.link_memory' (which creates links) and 'memory.pr.linked_memories' (which likely lists memories linked to a PR, the inverse). The purpose is specific and precise, though it could be slightly improved by explicitly stating it is a read-only retrieval operation.

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 no guidance on when to use this tool versus its alternatives. With siblings like memory.pr.query (generic PR query), memory.pr.linked_memories (inverse listing), and memory.pr.link_memory (creating links), the description does not explain the specific scenario (e.g., 'Use this when you have a MemoryItem ID and need to see all associated PRs'). The user must infer the usage context from the name alone.

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