Search and cite the Chain of Thought podcast archive: full-text search over every episode transcript, episode lookup, and bounded transcript excerpts, with each result linked to its episode page on chainofthought.show. Read-only, no login or API key.
Scored across 4 tools
The four tools split cleanly along two axes: episodes vs transcripts, and search vs retrieval. Descriptions actively disambiguate the overlapping-looking pair by cross-referencing each other (e.g. get_episode explicitly says to use search_transcripts/get_transcript_excerpt for passages). No realistic misselection risk.
All names follow a strict verb_noun pattern (get_episode, get_transcript_excerpt, search_episodes, search_transcripts) with two clean verb families (get_* for retrieval, search_* for discovery). Consistent snake_case throughout.
Four tools is lean but exactly right for a read-only podcast archive: two searches and two fetches cover the whole surface with no redundancy. Every tool earns its place and nothing feels padded or missing.
Discovery and retrieval of episodes and transcripts are fully covered for a read-only archive, and no mutating operations are needed. Minor gap: there is no way to browse/list all episodes or index guests/companies directly, though search largely works around this.
Returns one episode by number or slug (a full chainofthought.show episode URL also works): title, date, duration, guests with companies, summary, chapters with timestamps, and links to the episode page, YouTube and audio. Does not return the transcript; use search_transcripts or get_transcript_excerpt for passages. Cite the url.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | No | Episode slug or full chainofthought.show episode URL. | |
| episode | No | Episode number. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: the explicit exclusion of transcript content, acceptance of a full URL in addition to slug/number, and the instruction to cite the url. That is meaningful value beyond the structured fields.
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?
Three sentences, no filler. The core purpose leads, the returned-field list follows, and the exclusion/alternative and citation instruction are packed into the remaining clauses.
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?
There is no output schema, so the description must describe the return surface, and it does so thoroughly while also covering the key exclusion and the cross-tool escape hatch. An agent has everything needed to select and call it correctly.
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 100% and both parameters are documented in the schema, including the URL-accepting behavior of 'slug'. The description restates 'by number or slug' without adding syntax or format detail beyond the schema, so the baseline 3 applies.
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?
States a specific verb and resource ('Returns one episode by number or slug') and then enumerates exactly what comes back: title, date, duration, guests with companies, summary, chapters with timestamps, and links. This is clearly distinguishable from the transcript-oriented siblings.
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?
Explicitly states the negative case ('Does not return the transcript') and names two alternatives (search_transcripts, get_transcript_excerpt) with the condition that selects them. It does not, however, address when to prefer this tool over the sibling search_episodes, so routing guidance is incomplete but strong.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns up to 16 consecutive transcript segments from one episode around a timestamp (m:ss or h:mm:ss), a segment_index from search results, or a passage url or its #t- anchor. Defaults: 2 segments before and 5 after. Each segment has its own url to cite.
| Name | Required | Description | Default |
|---|---|---|---|
| at | No | Segment index from search results, passage URL or #t- anchor, m:ss or h:mm:ss. | |
| after | No | Segments after the anchor, 0 to 10. | |
| before | No | Segments before the anchor, 0 to 5. | |
| episode | Yes | Episode number. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and a closed-world non-destructive read, so the safety profile is covered. The description adds genuine behavioral context beyond that: the hard 16-segment ceiling, the default 2-before/5-after window, and the fact that each returned segment carries its own citable URL. It does not describe ordering or what happens when the window runs off the end of an episode.
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?
Two tight sentences, front-loaded with the resource and its scope, then the accepted anchor forms and defaults. Every clause carries information — the segment cap, the anchor sources, the defaults, and the citation affordance — with no restatement of the title.
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?
No output schema exists, but with full annotation coverage and 100% schema description coverage the description only needs to sketch the return shape, which it does by noting each segment has its own URL to cite. The main residual gap is failure behavior for an out-of-range timestamp, anchor or segment index, which an agent would want to know before calling.
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 100%, so the baseline is 3 and the schema already documents 'at', 'before', 'after' and 'episode'. The description adds real value the schema does not: the combined clipping rule of 16 segments total (max 5 before + max 10 after + the anchor) and the default window of 2/5, which lets an agent reason about output size without reading both parameter bounds.
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?
States a specific verb and resource ('Returns up to 16 consecutive transcript segments from one episode') plus the anchor types accepted, so an agent can tell this is a windowed fetch around a known point rather than a search. It does not explicitly name sibling tools like search_transcripts, so differentiation is inferred from the anchor semantics rather than stated.
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 effectively tells the agent when to use it by naming the inputs it consumes: 'a segment_index from search results, or a passage url or its #t- anchor' — establishing a clear search-then-excerpt workflow and distinguishing it from search tooling. It stops short of stating explicit exclusions or naming the alternative tool for other cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Finds Chain of Thought episodes by topic, guest name, company, title or chapter title. Returns up to 20 episodes ranked by relevance with number, title, date, guests, a short summary, matching chapter titles and the episode page url to cite.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum episodes, 1 to 20. | |
| query | Yes | Topic, guest, company, title or chapter words. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description goes beyond that by disclosing the cap of 20 results, relevance ranking, and the exact fields returned, which annotations cannot convey.
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?
Two sentences, no filler, and the primary action is front-loaded ahead of the return-format detail. Every clause carries information.
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?
With no output schema, the description usefully explains the return shape (number, title, date, guests, summary, matching chapters, URL). Inputs are fully covered by schema plus description. Only the lack of routing guidance versus siblings keeps it from being complete.
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 100%, so both parameters (query, limit) are already documented in the schema, including the 1-20 range. The description lists searchable fields and the 20-result cap, slightly reinforcing the query and limit, but adds no syntax or format guidance beyond the schema. Baseline 3 is appropriate.
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?
States a specific verb and resource ('Finds Chain of Thought episodes') plus the fields searched (topic, guest name, company, title, chapter title). It is clear what the tool does, but it does not differentiate itself from the close sibling search_transcripts, which also searches by content.
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 usage (find episodes by topic/guest/company) but never states when to prefer this over search_transcripts or get_episode. No exclusions or prerequisites are given, so the agent must infer routing from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Full-text search over Chain of Thought transcripts. Returns up to 20 passages ranked by relevance, each with episode number and title, guests, speaker, timestamp, a snippet of about 600 characters, and a url for that moment on the episode page (#t-N). Cite that url. Optional episode limits the search to one episode. Use get_transcript_excerpt for context. Transcripts are machine-generated; check exact quotes against the recording.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum passages, 1 to 20. | |
| query | Yes | Words to find in transcript passages. | |
| episode | No | Restrict to this episode number. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: it discloses the ranking behavior, the ~600-character snippet, the '#t-N' URL anchoring scheme, a citation instruction, and the important caveat that transcripts are machine-generated and quotes should be checked against the recording.
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?
Front-loaded with the purpose, then output shape, then citation guidance, then sibling routing, then the accuracy caveat. Five dense sentences with no filler; every clause carries actionable information.
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?
With no output schema, the description fully compensates by enumerating the returned fields and the URL format, and it flags the reliability caveat about machine-generated text. An agent has everything needed to call it and to cite results correctly.
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 100%, so query, limit and episode are already documented with ranges and defaults, making 3 the baseline. The description restates the episode restriction but adds no syntax or format detail, and notably omits the limit parameter that the schema exposes.
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?
States a specific verb and resource ('Full-text search over Chain of Thought transcripts') plus the exact shape of the result: up to 20 ranked passages with episode number, title, guests, speaker, timestamp, snippet and URL. This is clearly distinguishable from siblings like search_episodes and get_transcript_excerpt.
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?
It names a follow-up alternative ('Use get_transcript_excerpt for context') and explains the optional episode scoping, giving the agent clear routing context. It stops short of stating when NOT to use this tool, e.g. why to prefer search_episodes, so it does not reach a full 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_episodeget_transcript_excerptsearch_episodessearch_transcripts
Add one secure layer between your agents and this server.