search_similar_screenshotsSearch for similar screenshots by hash.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| hash_type | No | phash | |
| hash_value | Yes | ||
| max_distance | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, open-world, idempotent, and non-destructive behavior. The description adds only the 'by hash' mechanism but does not disclose how similarity is calculated, what max_distance means, or any limitations on hash types. This is minimal additional context beyond the annotations.
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 a single efficient sentence with no filler. It is front-loaded with the core action, though extremely brief.
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 tool has four parameters and an output schema, but the description provides almost no operational context. It doesn't explain how to set similarity tolerance, what hash types are supported, or how results are ordered. Despite annotations covering safety, the description leaves substantial gaps for a similarity-search tool.
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 0% schema description coverage, the description must explain the parameters. It mentions 'by hash' but doesn't clarify the meaning of hash_type (e.g., phash), max_distance, or limit. This is insufficient given the four-parameter 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?
The description uses a specific verb ('Search'), resource ('screenshots'), and method ('by hash'), clearly distinguishing it from sibling tools like 'search_by_screenshot_hash' (exact match) and other similar-search tools for different resources.
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 on when to use this tool versus alternatives. The description does not mention exact-match search or explain the similarity concept, leaving the user to infer from the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Many tools overlap in purpose, particularly the JS fingerprint search functions (e.g., search_js_fingerprint_by_md5 and search_jsfingerprints_by_md5) which are nearly identical. The large number of get_* and search_* tools for various statistics also creates boundary ambiguity.
The verb_noun pattern is mostly followed, but there are significant inconsistencies: 'jsfingerprints' vs 'js_fingerprints' vs 'js_fingerprint', and the occasional use of 'find' instead of 'search' (e.g., find_js_fingerprint_similar_by_hash). This mixed style makes it hard to predict tool names.
With 128 tools, the server is severely over-scoped. Many tools could be combined (e.g., all search_jsfingerprints_by_* variants) or parameterized. The sheer number overwhelms an agent and suggests poor API design.
The core URL scanning workflow (submit, retrieve results, search, analyze) is well covered, including detailed sub-analyses like malware, YARA, and JS fingerprints. Minor gaps include no scan cancellation or user-specific scan listing, but overall coverage is strong.