steve-filter

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

With no annotations provided, the description carries the behavioral disclosure burden. It clearly discloses the return format (PASS/CAUTION/FAIL, 0-100 score, risk level, reasons) and explicitly states a limitation (no alpha promise, risk elimination/winner concentration focus). This is strong for a read-only check tool, though it doesn't mention data sources or rate limits.

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 compact and information-dense, front-loading the main action and listing filters and outputs efficiently. The 'NOT' clause adds important boundary context without excessive length, though the Turkish phrasing is somewhat dense and jargon-heavy.

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?

The description explains root purpose, the main filters, the output shape, and the tool's limitations, which is sufficient for an agent to select and invoke it correctly. Lacking an output schema, the description compensates by describing the return values. It could further clarify when 'fresh' should be set to false, but overall it is reasonably 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?

Schema description coverage is 100%, so the baseline is 3. The description does not add parameter-specific meaning beyond the schema, but given both 'mint' and 'fresh' are already described in the input schema, the description's lack of parameter detail is acceptable.

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 it evaluates Solana memecoins through multiple risk filters and specifies the output (PASS/CAUTION/FAIL, 0-100 score, risk level, reasons). It is specific enough to distinguish it from the sibling check_deployer, though it does not explicitly name the sibling or draw a contrast.

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 implies usage for risk screening and winner concentration in a high-variance memecoin universe, and it explicitly warns that it does not promise alpha. However, it does not explicitly state when to prefer check_coin over check_deployer, leaving the selection decision partially to inference.

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

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

With no annotations the description carries the behavioral burden. It openly states that the tool returns a 0-100 reputation score, a tier, and historical launch/win/rug counts, and even explains the data-backed signal (prior-winner 2.8x lift). It does not discuss rate limits or failure modes, but for a read-only reputation lookup this is reasonably transparent.

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 compact sentences lead with the action, then output, then the data-backed rationale. There is no filler or redundant restatement.

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 one-parameter tool with no output schema, the description covers the input type and the return values sufficiently for an agent to call it and interpret the result. It does not specify address format or edge-case behavior, but those are not critical given the schema's 100% parameter coverage.

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 fully documents the single creator parameter as a wallet address at 100% coverage, so the description adds little new syntax. It adds context by calling it a creator/deployer address and linking it to past launches, which is useful but not necessary.

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?

States a specific verb and resource: 'değerlendir' a creator/deployer address's past reputation, and enumerates concrete outputs (0-100 score, tier, launch/win/rug counts). This makes it clearly distinct from the sibling check_coin, which by name targets a coin rather than an address.

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 'seri-dud kaçınılmalı' note implies a vetting use case, but there is no explicit when-to-use statement and check_coin is never mentioned as an alternative. The intended decision boundary between checking a coin and checking its deployer is left to inference.

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