Fetches patent evidence and stores a compact result in a SQLite session for subsequent retrieval.
Získa patentové dôkazy a uloží kompaktný výsledok do SQLite session.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | ||
| run_id | No | ||
| attempt_no | No | ||
| session_id | No | ||
| max_fetches | No | ||
| max_results | No | ||
| source_type | No | patent | |
| english_query | No | ||
| fetch_timeout_ms | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.9.5Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the burden of behavioral disclosure, and it does state the main side effect: writing a compacted result to SQLite. However, it does not disclose whether existing session data is overwritten or appended, whether network fetching can fail or time out, or what session state is required before calling the 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?
The single sentence is concise and front-loaded with the core action and destination. It contains no filler, though its brevity comes at the cost of omitting important operational and selection guidance.
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 nine-parameter tool with no annotations and no parameter descriptions, this is clearly under-specified. An agent cannot determine required session fields, how attempt_no or max_fetches affect behavior, or when this tool should be chosen over the sibling evidence tools.
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 0% and the description names none of the nine parameters. Field names like session_id, run_id, attempt_no, and max_fetches are suggestive, but the description provides no mapping between these parameters and patent retrieval or session storage behavior, leaving substantial ambiguity.
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 ('Získa' - gets) and identifies the resource (patent evidence), while also stating the outcome: storing a compact result into a SQLite session. It is clear enough to distinguish this from unrelated tools, though it does not explicitly differentiate it from the sibling evidence_to_session tools beyond the patent scope.
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 publication_evidence_to_session or web_evidence_to_session, nor when it fits into the research session workflow. The intended usage must be inferred entirely from the tool name and sibling context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.