Mooncatcher Wire

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

No annotations are provided, so the description carries the full burden. It describes the returned content categories but says nothing about freshness, pagination behavior, auth requirements, or whether the board is a fixed snapshot versus a queryable collection — meaningful gaps for a zero-annotation tool.

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 with the content list front-loaded and no filler. It is appropriately sized, though the second sentence about the website is of marginal utility to an agent.

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 read-only overview with no output schema, no annotations, and one undocumented parameter, the description explains the return content reasonably but omits usage routing and the limit semantics, leaving the agent with avoidable ambiguity.

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 'limit' parameter has 0% schema description coverage and is never mentioned in the description. With low coverage the description is expected to compensate, and it does not explain what is being limited or how it interacts with the 'top stories' list.

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 the resource (the crypto news board) and enumerates its contents: mood, counts, top stories by market impact, and AI digest. This distinguishes it as a composite/overview view, though it overlaps with the sibling mcw-get-digest by explicitly including 'the AI digest' without explaining the relationship.

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?

No when-to-use guidance at all. It never says to prefer this overview over mcw-get-digest, mcw-list-stories, or mcw-list-topics, despite the digest overlap being an obvious source of confusion for an agent choosing a tool.

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 must carry behavioral context. It discloses the return content well (overview, bull/neutral/bear split, per-ticker takeaways, clustered highlights), but says nothing about whether a board must be loaded first, freshness/generation timing, or cost — a meaningful gap with zero annotation coverage.

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 tight sentence that front-loads the resource and then the contents. It is a noun phrase rather than a full statement of action, but nothing is wasted.

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 usefully spells out the shape of the returned digest, which is the main thing an agent needs. The only gap is the implicit dependence on an already-selected 'current board'.

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. There is nothing for the description to disambiguate at the input level.

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 names a specific artifact (the AI-written market digest) and enumerates its contents, so an agent knows exactly what this returns. It does not explicitly distinguish itself from siblings like mcw-get-board or mcw-get-story, so it falls short of a 5.

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 explicit when-to-use guidance, no exclusions, and no mention of alternatives such as mcw-get-board or mcw-get-story. The phrase 'for the current board' only weakly implies a precondition (a board must be selected).

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 behavioral burden. It usefully discloses the return content (TSP review state and Moon Catcher Wire editor state if set), but omits not-found/error behavior and whether the call has side effects. Partial disclosure earns a middle score.

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 with no filler; the key retrieval mode and returned fields come first. Efficient, though slightly terse.

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 simple single-param getter with no output schema or annotations, the description is mostly adequate but leaves error handling and side-effect expectations unstated, which matters for agent confidence.

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%, so the description should compensate, but the sole parameter is self-evident and 'by its id' confirms its meaning. No format or validity details are added beyond that.

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 a specific verb (get), resource (story), and scope ('one story in full by its id'), which clearly separates it from the sibling mcw-list-stories. It does not name siblings explicitly, but the singular/retrieval framing is 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?

There is no explicit guidance on when to use this tool versus mcw-list-stories or mcw-search. The 'by its id' phrasing implies the precondition of already having an id, but no when/when-not or alternative routing is provided.

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 behavioral burden. It adds genuinely useful context that `topic` uses MCW's own keyword rules while `ticker` follows TSP, and that `breaking_only` keeps high-impact wires, but it says nothing about ordering, defaults, pagination via `limit`, or the return shape.

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 core statement, then parameter-by-parameter notes that each earn their place. The aside about TSP lacking a topic model is slightly verbose but informative rather than wasteful.

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 five-parameter list tool with no output schema and no annotations, the description covers filter semantics well but omits `limit`/pagination behavior, ordering, and default result size. An agent could call it correctly, but key operational details are absent.

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 only 40%, so the description must compensate. It meaningfully explains four of five parameters (ticker, topic, since_hours, breaking_only), including the TSP-vs-MCW distinction, but leaves `limit` and its bounds/default unexplained, so it does not fully close the coverage gap.

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 resource (stories) and that it returns filtered collections, and it distinguishes `topic` from `ticker` in a way that clarifies the tool's model. It does not explicitly contrast itself with the closest sibling, `mcw-search`, but the verb+resource and filter explanation are clear enough for an agent to select 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?

It routes the agent to `mcw-list-topics` for valid topic values, which is useful, but gives no guidance on when to use listing vs `mcw-search`, `mcw-get-digest`, or `mcw-get-story`. Usage is only implied through the filter semantics.

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 burden. It does add genuinely useful behavioral context — topics are locally defined keyword rules over headline and summary, because the upstream classifier only works by ticker — which tells the agent why topic hits behave differently from ticker hits. It still never states that this is a safe read-only enumeration or what the response shape is.

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 padding, but the structure is inverted for a tool definition: it opens with domain jargon ('TSP classifies only by ticker', 'representable upstream') instead of leading with what the tool returns. The most actionable fact — these are keyword rules over headline/summary — is buried mid-sentence.

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 list tool with no output schema, the description supplies useful interpretive context about what a topic identifier means, which is more than a bare restatement. It is still missing the basics an agent needs: that it returns the set of topic names/rules, and whether the set is static or tenant-specific.

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 disambiguate; schema coverage is 100% and the empty object schema is self-explanatory. Baseline 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 identifies the resource (Moon Catcher Wire topics and their underlying rules) but never states the action — it reads as an explanation of what topics are rather than 'returns the list of available topics'. An agent can guess the intent from the name/title, but the description itself never says what the call produces.

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 and no mention of any sibling. With mcw-list-stories, mcw-search, and mcw-get-digest available, an agent gets no signal about when listing topics is the right move versus searching or fetching stories.

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 it does add real behavioral value: case-insensitivity and the fact that matching is limited to headlines/summaries rather than full story text. However, it says nothing about result ordering, whether matches span the whole board or a topic, or what happens with an empty/missing query.

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 with no filler; the scope constraint (headlines and summaries, current board) arrives immediately. Every word earns its place, though the economy comes at the cost of completeness elsewhere.

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 search tool with no annotations, no output schema, and two undocumented parameters, the description is too thin: it omits result shape, ordering, the limit's default/cap, and the board context requirement. An agent could invoke it but would have to guess at nearly all of its behavioral contract.

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% for both parameters, so the description is the only source of meaning — yet it only implies a query string exists and never mentions 'limit', its default of 20, or its maximum of 60. The two most behaviorally consequential constraints of this tool are left entirely 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 (search) and the exact resource scope it covers (headlines and summaries of the current board), which lets an agent distinguish it from the retrieval-oriented siblings like mcw-get-story or mcw-list-stories. It stops short of explicitly naming an alternative, but the operation is 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?

There is no guidance on when to search versus browsing with mcw-list-stories/mcw-list-topics, nor any stated preconditions such as needing an active board. The 'current board' phrasing hints at a context dependency but never states it as a requirement.

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