art.memory.find_rejections

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

Since annotations are absent, the description must shoulder the full burden of disclosing behavior, but it only states that a search occurs. The description does not disclose what a 'rejection record' represents, what entity it belongs to, whether any implicit status filtering (e.g., excluding 'archived') happens by default, or what the shape of the results will be. For a non-read-only annotation-less tool, this is a meaningful gap, though it doesn't contradict anything.

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 seven words and wastes no words. It front-loads the action verb and noun phrase immediately, which an agent can parse in a single pass. For such a simple filtering tool, this level of concision is appropriate, though it leans toward terse.

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 low-complexity search endpoint with 5 optional, well-documented parameters, the description is mostly sufficient. The main shortcoming is the domain-specific term 'rejection records,' which is never elaborated upon (e.g., rejection of what — assets, styles?), and there is no mention of which sibling tools it complements. An agent familiar with the 'art.memory' domain will manage, but a novice agent might misinfer the resource scope.

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 coverage is 100%, and each parameter has a 'Filter by...' description, establishing a baseline of 3. The description's 'optional filters' correctly mirrors the schema's 0 required parameters but adds no additional meaning, such as how filters combine when multiple are provided, or whether the filters are inclusive or exact-match.

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 a precise verb ('Search') and resource ('rejection records'), making the core action clear and distinct from write operations. However, it doesn't explicitly differentiate from the very similarly-named sibling art.memory.get_rejection, which could plausibly perform the same action in a different mode.

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?

No guidance is provided for when to choose this tool over alternatives like art.memory.get_rejection, art.memory.find_references, or art.asset.find. The phrase 'with optional filters' implies a parametrized search but never states when this is the right call versus a simple get or lookup.

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