AI Workflow Feed MCP

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety and external-scope are covered structurally. The description adds genuinely useful context not in annotations: it returns metadata (last successful fetch, failures, staleness) rather than full text, and warns that not all manual sources are covered. It doesn't describe output shape or failure semantics, so a 3 is appropriate.

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 with no filler; the positive scope is front-loaded and the exclusion ('Metadata only, not article full text') is stated immediately after. Every clause conveys actionable boundary 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?

There is no output schema, so the description is the sole source of information about return values. It names three categories (last successful fetch, failures, staleness) but doesn't describe structure or format. Given the tool is a zero-param read with annotations covering safety, this is adequate but leaves the return shape underspecified.

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?

Zero parameters means there is no parameter semantics to document, so the baseline is 4. The description correctly implies the tool takes no input, which aligns with the empty schema.

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 ('Read the latest cloud snapshot of selected public sources') and clarifies scope with 'Metadata only, not article full text'. It doesn't explicitly distinguish itself from siblings list_sources and recent_posts, but the snapshot-fetch-status framing is distinctive enough for an agent to infer the difference.

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 by the description — it's the tool for checking fetch health/staleness of public sources. However, there's no explicit when-to-use guidance and no mention of the alternatives (list_sources, recent_posts), so the agent must infer that this is diagnostics rather than content retrieval.

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 useful catalog semantics: exclusions (Threads not included), manual-only handling by recent_posts, and daily_snapshot overlap, which go beyond structured data. It stops short of describing exact return shape, but no output schema exists either.

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 dense sentence with the core action front-loaded ('List the source catalog'), followed by scoping details. Every clause (provenance, availability, manual-only, daily_snapshot, Threads exclusion) carries information; no filler.

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 zero-parameter, no-output-schema listing tool, the description covers content, provenance, availability, and key exclusions well. Minor gap: it doesn't enumerate the returned fields explicitly, but it implies them sufficiently.

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 the baseline is 4. Nothing in the description contradicts or under-specifies an input surface that already has 100% schema coverage.

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 ('List') and resource ('source catalog') and clarifies the content dimension (categories, provenance, availability). The scope is easy to distinguish from recent_posts and daily_snapshot, though the phrase 'automatic availability' is slightly opaque.

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 rather than stated; it explains how sources relate to recent_posts (manual-only not fetched) and daily_snapshot (some appear separately), but does not explicitly say 'use this to discover available sources before querying.' No direct when/when-not guidance for the tool itself.

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 cover read-only and open-world behavior, so the bar is lower, yet the description still adds real value: excerpts are untrusted content (a prompt-injection warning), they are not full articles, and pagination terminates when next_source_offset is null. It omits result volume/format expectations, but the safety-relevant context is well disclosed.

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 compact sentences, front-loaded with purpose, then the category rule, pagination instruction, and trust caveat. Every sentence carries information, though the parenthetical about category assignment is dense.

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, and the description explains the cursor field and excerpt nature but not the shape of returned batches or the semantics of half the parameters. Adequate for calling it, incomplete for calling it optimally.

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% across 7 parameters, so the description must carry the load. It explains category values and the offset cursor, but leaves days, limit, query, and the 44-value sources enum entirely undefined, which is a substantial gap for a filtering/retrieval tool.

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 — retrieving recent posts from fixed public feeds — and clarifies the feed model (categories belong to sources, not articles). It doesn't explicitly name the list_sources sibling, only alluding to it via 'Manual-only sources are listed separately', so differentiation is inferential 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?

Gives concrete operational guidance: pick category ai_development or agent_flow for source batches, and follow next_source_offset until null. However, it never says when to use this tool versus list_sources, nor how to choose between the sources, category, and query parameters.

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