Field Notes podcast library

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds value beyond that by disclosing the shape of the payload — per-language titles, summaries, chapter lists with page anchors and YouTube timestamps, plus Markdown and JSONL link variants — which matters because there is no output schema.

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?

A single front-loaded sentence: purpose first, then the returned payload. Dense but tightly packed with useful nouns; slightly heavy on parenthetical detail, yet every clause describes real return content an agent would want to know.

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 carries the return-value burden and does so adequately by enumerating the content types and link formats. It does not cover failure behavior for unknown ids or payload size, which are minor gaps for a single-item read.

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 the schema's own id description supplies the example and provenance (YouTube video id from search results). The description adds nothing about the id parameter beyond what the schema already says, so 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: retrieve a single episode by id, and lists the concrete contents returned (titles, summaries, chapter list, full-text links). It is distinguishable from search_episodes and the list_* siblings by being a single-item fetch, though it never names them explicitly.

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?

Usage is implied: use this when you already have an episode id (the schema even says 'a YouTube video id from search results'), which hints at a search-then-fetch flow. There is no explicit statement of when to prefer search_episodes or the list tools, and no mention of what happens with an invalid id.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds substantive behavior beyond that: the record fields returned (episode counts, latest appearance date) and the sort order, which an agent needs to interpret results.

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 compact sentences, zero filler; the resource and return shape come first and the filtering hint closes it out.

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 two-parameter read-only list tool with no output schema, the description conveys enough (what a row contains, ordering, filter semantics) to invoke and interpret it. The only omission is guidance on the limit parameter, which is undocumented everywhere.

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 50%: query is fully documented in the schema, leaving limit undocumented in both places. The description's 'filter with a partial name' only restates the query parameter without adding syntax or matching behavior, and says nothing about the 1-50 limit cap or default page size.

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?

Uses a specific verb (list) and resource (hosts and guests in the library), and adds value beyond the name by clarifying that 'people' means hosts and guests, that results carry episode counts and latest appearance date, and that ordering is most-frequent-first. It is clearly a different resource from the episode- and topic-oriented siblings, though it does not name them.

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?

'Filter with a partial name' gives an implied usage cue for the query parameter, but there is no explicit when-to-use vs. siblings guidance (e.g. versus search_episodes or get_episode) and no statement about defaults or when to omit the query.

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

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), but the description adds two genuinely useful behavioral facts: the response carries episode counts per topic, and topic names are Chinese rather than English, which materially affects how an agent matches user queries.

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?

A single sentence, front-loaded with the core action, and the parenthetical examples are short and earn their place by preempting the Chinese-name confusion.

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 parameters and no output schema, the description covers the essentials: what is listed and that counts come back. Minor omissions such as ordering or whether the list is exhaustive for a closed-world corpus are not addressed.

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 tool takes zero parameters, so there is nothing for the description to clarify beyond what the empty schema already conveys; the baseline of 4 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?

The description uses a specific verb and resource ("List all topics and series") and explicitly states the payload includes episode counts. It doesn't name the sibling tools it complements (search_episodes, list_people), so it falls just short of full sibling differentiation.

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?

Usage is only implied: an agent can infer this is the discovery step before searching or fetching episodes, but the description never says when to call this versus search_episodes or list_people, nor does it state any prerequisites.

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

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

Annotations already declare readOnlyHint and openWorldHint=false, so safety is covered. The description adds real value beyond that: it enumerates what each match contains (title, people, date, topics, summary, matching chapters, Markdown/YouTube links) and warns that summaries are mostly in Chinese – a non-obvious trait affecting how an agent presents results.

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, front-loaded with capability, followed by return contents and one high-value usage hint. Nothing is redundant with the schema and every sentence carries information an agent would otherwise guess at.

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 compensates by listing the return fields and the full-text/YouTube links. Combined with the language note and the person-query idiom, an agent has enough to select the tool, form queries, and interpret results without further probing.

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 it earns a baseline 3, but the description adds meaning beyond the schema: it frames `person` as the key to a specific query pattern and flags the Chinese-language bias of the underlying text, which informs how the agent should phrase queries. It doesn't explain `from`/`to` or `limit` beyond the schema, capping it below 5.

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 (search) and resource (podcast/conference episodes) and scopes the domain (AI, investing, crypto, startups, macro). Distinguishes from siblings: get_episode fetches one episode, list_people/list_topics enumerate, while this searches over episodes by keyword/person/topic/date.

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?

Gives a concrete usage scenario – 'Use `person` to answer which podcasts has X appeared on' – which routes the agent to the right parameter for that question shape, and implies `topic` values come from list_topics. It doesn't state exclusions (e.g., use get_episode once you know the ID), so it falls short of explicit when-not guidance.

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