get_topic_seriesGet recent attention history for a Topic.
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | End of time window (ISO 8601) | |
| from | No | Start of time window (ISO 8601) | |
| measure | Yes | trend for hourly scores; rank for recorded Trend-rank changes | |
| topicId | Yes | Topic ID |
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | ||
| meta | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / measure / descriptionPrevious value: -"trend for hourly scores; emergence for retained pre-quarantine six-hour measurements (not breakout probabilities); rank for recorded Trend-rank changes"New value: +"trend for hourly scores; rank for recorded Trend-rank changes"Input schema / properties / measure / enumPrevious value: -[
- "trend",
- "emergence",
- "rank"
-]New value: +[
+ "trend",
+ "rank"
+]Output schema / properties / data / properties / basis / enumPrevious value: -[
- "hourly",
- "six_hourly",
- "rank_transitions"
-]New value: +[
+ "hourly",
+ "rank_transitions"
+]Output schema / properties / data / properties / measure / enumPrevious value: -[
- "trend",
- "emergence",
- "rank"
-]New value: +[
+ "trend",
+ "rank"
+]Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / properties / measure / descriptionPrevious value: -"trend for hourly scores; emergence for six-hour scores; rank for recorded Trend-rank changes"New value: +"trend for hourly scores; emergence for retained pre-quarantine six-hour measurements (not breakout probabilities); rank for recorded Trend-rank changes"Input schema / properties / measure / descriptionPrevious value: -"trend for hourly history; rank for recorded rank changes"New value: +"trend for hourly scores; emergence for six-hour scores; rank for recorded Trend-rank changes"Input schema / properties / measure / enumPrevious value: -[
- "trend",
- "rank"
-]New value: +[
+ "trend",
+ "emergence",
+ "rank"
+]Output schema / properties / data / properties / basis / enumPrevious value: -[
- "hourly",
- "rank_transitions"
-]New value: +[
+ "hourly",
+ "six_hourly",
+ "rank_transitions"
+]Output schema / properties / data / properties / measure / enumPrevious value: -[
- "trend",
- "rank"
-]New value: +[
+ "trend",
+ "emergence",
+ "rank"
+]Input schema / properties / from / descriptionPrevious value: -"Window start (ISO 8601)"New value: +"Start of time window (ISO 8601)"Input schema / properties / measure / descriptionPrevious value: -"Measurement series"New value: +"trend for hourly history; rank for recorded rank changes"Input schema / properties / to / descriptionPrevious value: -"Window end (ISO 8601)"New value: +"End of time window (ISO 8601)"Input schema / properties / topicId / descriptionPrevious value: -"Known Topic id"New value: +"Topic ID"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint=true and destructiveHint=false, so the tool is clearly safe for reading. The description adds the behavioral context that this retrieves 'history' (time-series data), which is beyond what the annotations specify. There is no contradiction with 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 concise sentence that immediately conveys the tool's purpose. It front-loads the key action and subject. It could potentially add a bit more context (e.g., what 'recent' means) without becoming verbose.
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?
Given the tool has an output schema (not shown but present), the description need not detail return values. However, it provides no guidance on time window handling or the interpretation of 'recent', nor does it explain the two measure options. The description is adequate for a tool with strong schema coverage and annotations, but leaves the agent guessing on default behavior (e.g., what happens if 'from' or 'to' is omitted?)
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%, so the schema fully documents all four parameters with descriptions and constraints. The description adds minimal parameter-specific value but confirms the overall intent ('recent attention history'). The measure enum is well-described, and date/time parameters are clearly specified. Baseline 3 plus minor extra context justifies 4.
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 'Get recent attention history for a Topic' clearly identifies the action (get) and resource (attention history for a topic). However, it uses the vague term 'recent' which is not precisely defined, and among siblings like 'get_topic' (which likely returns current state) and 'get_project_series', this does not strongly distinguish itself beyond the resource type.
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 the tool is for retrieving time-series data ('recent attention history'), suggesting it is for historical queries rather than current state. However, it provides no explicit guidance on when to use this tool versus alternatives like 'get_topic' (current state), 'get_intel' (different resource), or 'get_report'. No exclusion criteria or context signals are mentioned.
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 entity or action: single vs. list (get vs. list), intel vs. project vs. topic vs. report vs. cluster vs. vocabulary vs. credential check. No two tools have overlapping purposes; the descriptions clearly differentiate them.
Uses a consistent pattern: get_ for singular retrieval, list_ for plural searches/listing. Only 'me' deviates, but it's a standard name for credential checks. The pattern is predictable and easy to follow.
12 tools cover a focused domain (crypto intelligence) without unnecessary bloat. Each tool earns its place: core entities (projects, topics, intel), plus series, reports, vocabulary, clusters, and auth check. The count feels well-scoped.
The server provides a complete read surface for its domain: listing, searching, getting details, historical series, reports, and filter metadata. No obvious gaps for consuming intelligence (CRUD not expected in a read-only API).