Pull a batch of recent ISIR events (insolvency register publications) since the given event id. ISIR is an append-only feed — each call returns up to ~1000 events newer than since_id. Use last_id from response as next since_id. Useful for compliance monitoring or to back-fill an index.
| Name | Required | Description | Default |
|---|---|---|---|
| since_id | No | Last seen event id. Use 0 to start from the beginning of recorded ISIR history (~2008). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (readOnlyHint, openWorldHint), the description reveals key behaviors: ISIR is an append-only feed, each call returns at most ~1000 events, and the pagination contract via `since_id`/`last_id`. This significantly aids the agent in understanding expected results and proper invocation.
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 two sentences, front-loaded with the primary action and immediately followed by essential operational details. Every sentence earns its place, with no fluff or repetition of schema/annotation info.
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 read-only tool with one parameter and no output schema, the description covers purpose, usage pattern, feed characteristics, and relevant use cases. It adequately compensates for missing response schema by explaining the `last_id` cursor, making the tool self-contained for an agent.
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 describes `since_id` with default and minimum, achieving 100% coverage. The description adds valuable context about how to use the parameter in a looping pagination pattern, which goes beyond the schema's basic field description.
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 begins with a specific verb ('Pull') and resource ('batch of recent ISIR events'), clearly stating what the tool does. It also distinguishes itself from siblings by focusing on the event feed polling pattern, unlike checking or searching specific records.
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 explicit usage guidance: 'Use `last_id` from response as next `since_id`' and mentions use cases (compliance monitoring, back-filling an index). However, it does not explicitly mention alternatives or when not to use this tool, so it falls short of full differentiation.
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.
Each tool targets a distinct operation: checking a company by IČO, polling recent events, and searching by person. No functional overlap.
All tool names follow a clear verb_noun pattern (check_ico_insolvency, poll_isir_events, search_person_insolvency), ensuring predictability.
Three tools precisely cover the key interactions with the ISIR register without unnecessary bloat or missing essentials.
The set covers the three core use cases for this read-only register: company lookup, person search, and event monitoring. No obvious gaps for its domain.