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

With no annotations, the description carries the full burden and does well: it discloses permanence by default, reappearance after ttl expiry, that receipts are NOT verified server-side, and that unknown IDs are segregated into a missing bucket. Undisclosed gaps remain around idempotency, permissions, and what happens if an event is acked twice.

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?

Four short, front-loaded lines: action plus valid states first, then ttl behavior, then the delivery_ref constraint, then the missing-ID behavior. No filler or repetition; every sentence adds a distinct rule.

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 5-parameter mutation tool with no annotations and no output schema, this covers state semantics, ttl, receipt requirements, failure exclusions, and partial return behavior (missing IDs). The unaddressed consumer parameter and lack of auth/permission context are the remaining gaps.

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 0%, so the description must compensate. It meaningfully explains reason (full enum), ttl_hours, and delivery_ref — including a requirement not visible in the schema. However, the consumer parameter is never mentioned, leaving one of five parameters fully undocumented.

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 (记录/acknowledge) and resource (条目/entries) and enumerates the four valid ack states (processed, read, discarded, delivered) — value the schema does not provide since it defines reason as an unconstrained string. It does not explicitly differentiate from siblings like poll_feeds or get_proactive_events, but the ack semantics are unambiguous.

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?

Provides concrete when/when-not rules: delivered requires a real delivery_ref, and events merely queued for push or with failed sends must NOT be marked delivered. It also explains the default (permanent consumption) versus ttl_hours behavior. It offers no explicit routing against sibling tools, which holds it below a 5.

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?

With no annotations, the description carries the full burden. It does disclose meaningful behavior: the URL protocol restriction, that delete/pause need an exact name or source_id, and that subscribed feeds are not auto-pushed (poll_feeds required). It omits permission/auth needs, what delete destroys, and reversibility of pause.

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-loads the action list, then layers constraints as short lines. No filler sentences; each line carries an operational fact. Slightly terse for the number of parameters, but well-structured.

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 no annotations, no output schema, and 6 undocumented parameters, the description covers the action vocabulary, the identification semantics for delete/pause, and the poll workflow, but leaves the meaning of 'note'/'poll_interval_seconds' and what 'list' returns unexplained. Adequate but with clear gaps.

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 0% across 6 parameters, so the description must compensate. It explains url, name/source, and the action values, but says nothing about 'note' or 'poll_interval_seconds', leaving two parameters completely undocumented in both schema and text.

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+resource (manage RSS/Atom subscriptions) and enumerates the concrete actions (list, subscribe, unsubscribe, pause, resume), so the agent knows exactly what it operates on. It does not explicitly disambiguate from feed_query or feed_status, though the poll_feeds reference partially differentiates it.

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?

Provides operational constraints ('URL must be HTTP/HTTPS RSS or Atom', 'delete and pause use exact name or source_id') and routes to the sibling poll_feeds for collection. However, it never says when to use feed_manage versus feed_query or feed_status, so use-case selection is left to inference.

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?

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses that the query does not trigger network collection and lists the fields returned, but says nothing about authentication, rate limits, pagination behavior despite page/limit/page_size params, or how 'failed sources' surface.

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?

Compact and front-loaded: purpose, then the no-network constraint, then the routing hint, then the return fields. Every sentence earns its place, though the action list is packed inline rather than formatted for scanning.

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 rightly enumerates returned fields (title, summary, original text, publish time, event_id). However, for a 6-parameter tool at 0% schema coverage, the missing pagination and source/keyword semantics leave the definition incomplete for reliable invocation.

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 0%, so the description must compensate, yet it only indirectly names the action values (latest/search/summary/sources/catalog). The other five params (page, limit, source, keyword, page_size) are left with no meaning beyond their bare names and defaults.

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 (查询/query) and resource (已缓存的订阅内容/cached subscription content) and enumerates the five modes (latest, search, summary, sources, catalog). It clearly contrasts with the network-fetching sibling poll_feeds, letting an agent distinguish it without opening a schema.

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 covers when-to-use (query cached content), when-not (does not trigger network collection), and the alternative path (call poll_feeds first to refresh, then check failed sources). Nothing is left to inference.

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?

No annotations are provided, so the description carries the full behavioral disclosure burden. It lists returned fields but omits whether this is a safe read-only operation, what permissions are needed, or what an empty/default source does.

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 sentence that front-loads the verb and enumerates the returned fields without filler. It is appropriately sized for a simple status lookup.

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?

Because there are no annotations and no output schema, the description reasonably names the fields the tool reports. However, it leaves the optional source parameter ambiguous and does not help an agent choose among sibling feed tools.

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 single parameter, source, has 0% schema description coverage. The description mentions 来源 but does not explain expected value format, whether the empty default string means all sources, or whether the parameter is required.

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 states the verb 查看 and the resource 来源, then enumerates the status fields: latest collection time, success time, failure reason, and cache count. The purpose is clear, but it does not explicitly distinguish itself from siblings such as feed_query or feed_manage.

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?

There is no when-to-use guidance, no condition for selecting this tool over feed_query or poll_feeds, and no prerequisites. Usage is only implied by the word 状态.

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?

With no annotations, the description carries the full burden and does disclose the key side-effect profile: it does not fetch data, does not send messages, and does not auto-acknowledge. It also discloses the 36-hour window and the consumption filter. Missing are ordering, pagination, or idempotency details.

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 short clauses, front-loaded with the scope (36 hours, unconsumed) followed by the side-effect disclaimers. Efficient, though the trailing newline and terse fragments make it slightly less polished than it could be.

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 and no annotations, so the description should ideally say what a candidate event looks like and in what order results arrive; it does not. It covers purpose, window, side effects, and consumer identity, which is adequate but leaves return shape and limit semantics unaddressed.

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 0%, so the description must compensate. It does explain that consumer should be the target session's session_key, but adds nothing about limit (default 20) or its units/semantics, leaving half the parameters undocumented in both places.

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 with scope: read candidate content from the last 36 hours not yet consumed by this consumer. The consumption/window framing gives real meaning beyond the name, though it doesn't explicitly contrast with siblings like poll_feeds or feed_query.

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?

Implies usage by telling the caller to pass the target session's session_key as consumer and that the tool does not auto-ACK (implying acknowledge_events must be called separately). However, it never states when to use this versus poll_feeds/feed_query/feed_status, so the routing guidance is only inferable.

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?

With no annotations, the description carries the full burden and does well: it discloses the per-call batch cap of four, the rotation policy, the failure behavior (old cache retained, reason logged), and the continuation condition. It omits permission/auth requirements and any rate-limit beyond the batch size.

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?

Four short, front-loaded sentences covering batch scope, the force override, return fields, and error/continuation behavior. Nearly every sentence earns its place; only the enumerated return keys veer toward output-schema territory.

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 no annotations and no output schema, the description usefully enumerates return keys (ok, failed, remaining, per-source results) and failure semantics. The main gap is the undocumented `source` parameter, which an agent cannot interpret confidently.

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 0%, so the description must explain both parameters. It explains force well (ignores fetch interval) but says nothing about the `source` parameter's purpose or acceptable values, leaving half the surface undocumented in both schema and 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?

States a specific verb and resource (poll due RSS/Atom sources) plus concrete scope: at most four per call, rotated by last fetch time. This clearly distinguishes it from siblings like feed_manage, feed_query, and feed_status, 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?

Gives actionable when-to-use signals: call repeatedly while remaining>0, and set force=true to bypass the fetch interval. It does not, however, contrast itself against the sibling tools (feed_query, feed_status) for read-vs-poll decisions.

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