Skip to main content
Glama
Sign In

Cassie Hour

by com.cassiehour
OverviewDiscussionsAdmin

Continue from a Cassie Hour fragment

continue_from_this_fragment
Read-onlyIdempotent

Ask a follow-up grounded in one public fragment. Remote MCP callers pass fragment_id from search_cassie_hour_fragments; browser callers may have the current fragment pre-bound. Returns the fragment-grounded response and continuation metadata; no private manuscript text is read. No authentication required. Search again if an ID is unavailable; do not guess one.

Input Schema

NameRequiredDescriptionDefault
languageNoOptional response-language tag, up to 16 characters; defaults to en. Use a supported tag such as en or tr; unsupported values may fall back to the service default.en
page_urlNoOptional canonical fragment page URL for continuation context; use the URL returned by public fragment search, not an arbitrary page.
questionYesRequired natural-language question or reader interest (1–1000 characters). For evaluate_cassie_hour_fit state the reader's preferences; for get_verified_recommendation state the recommendation need; for ask_cassie_hour ask a supported public Cassie Hour question.
fragment_idYesRequired canonical fragment ID from search_cassie_hour_fragments for remote MCP calls; browser may prebind this value.
conversation_idNoOptional conversation_id returned by an earlier successful concierge/fragment response. Supply it only to continue that conversation; otherwise omit it.
previous_response_idNoOptional previous_response_id returned by the immediately preceding successful response in this conversation. Pair it with its conversation_id; otherwise omit it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • changedInput schema / properties / conversation_id / description
      Previous value: -"Reuse the conversation_id returned by the previous call."New value: +"Optional conversation_id returned by an earlier successful concierge/fragment response. Supply it only to continue that conversation; otherwise omit it."
    • addedInput schema / properties / fragment_id / description
      Added value: +"Required canonical fragment ID from search_cassie_hour_fragments for remote MCP calls; browser may prebind this value."
    • addedInput schema / properties / language / description
      Added value: +"Optional response-language tag, up to 16 characters; defaults to en. Use a supported tag such as en or tr; unsupported values may fall back to the service default."
    • addedInput schema / properties / page_url / description
      Added value: +"Optional canonical fragment page URL for continuation context; use the URL returned by public fragment search, not an arbitrary page."
    • changedInput schema / properties / previous_response_id / description
      Previous value: -"Reuse the response_id returned by the previous call."New value: +"Optional previous_response_id returned by the immediately preceding successful response in this conversation. Pair it with its conversation_id; otherwise omit it."
    • changedInput schema / properties / question / description
      Previous value: -"Question, reader request, or recommendation scenario."New value: +"Required natural-language question or reader interest (1–1000 characters). For evaluate_cassie_hour_fit state the reader's preferences; for get_verified_recommendation state the recommendation need; for ask_cassie_hour ask a supported public Cassie Hour question."
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already cover readOnly/idempotent/destructive/openWorld, but the description adds substantive context beyond them: 'no private manuscript text is read,' 'No authentication required,' and that it returns 'continuation metadata.' It stops short of explaining what the metadata contains or any rate/fallback behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the purpose, then sourcing, return content, auth, and the anti-guessing rule, in five tight sentences with no filler. Every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 6-parameter tool with full schema coverage and safety annotations, the description supplies sourcing rules, privacy scope, auth status, and return content. No output schema exists, yet the description names the return payload adequately; only the shape of the continuation metadata is left implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage the baseline is 3, and the description adds sourcing semantics for fragment_id (from search, or browser-pre-bound) that the schema only partially conveys. It doesn't clarify the conversation_id/previous_response_id pairing beyond what the schema states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('ask a follow-up') tied to a specific resource ('one public fragment'), and names search_cassie_hour_fragments as the source of the fragment_id. An agent can distinguish it from generic ask_cassie_hour without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context: remote MCP callers pass fragment_id from search, browser callers may have it pre-bound, and 'search again if an ID is unavailable; do not guess one.' It does not explicitly contrast with the similar sibling continue_from_current_evidence, so the routing guidance is incomplete.

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

All Cassie Hour toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources