ShadowGraph

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds two useful traits beyond them: it is free to call, and results are limited to 'recent' filings from an official source. It says nothing about latency, coverage window, or empty 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 short sentences, front-loaded with the cost signal and then the core action; no filler. Slightly terse rather than padded, which is appropriate.

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?

An output schema exists, so return values need not be described, and annotations carry the safety profile. Still missing: what a 'supported' symbol is, the meaning of the limit parameter, and the recency window, which leaves an agent guessing at the edges.

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%: 'symbol' is documented with examples, but 'limit' (1-10) has no schema description. The word 'recent' loosely conveys that a limit exists and bounds recency, but neither the default nor the max is stated in prose, so the description only partially compensates.

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 clear verb ('Return'), a specific resource ('recent official SEC EDGAR filings'), and the scoping input ('for a supported company symbol'). It does not differentiate from any sibling, but the siblings are unrelated tools so that is a minor gap.

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 only guidance is the cost signal 'Free.' and the vague qualifier 'supported company symbol'. There is no statement of when to use this versus alternatives, nor any prerequisite (e.g., what makes a symbol 'supported' or that data is US-only).

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 (readOnly=true, idempotent=true, destructive=false, openWorld=true), lowering the burden. The description adds a genuinely important behavioral fact not in the annotations: the $5.00/call cost, which materially affects invocation decisions, plus the breadth of the returned pack. It stops short of rate limits or output format specifics, so 4 rather than 5.

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 that front-loads the cost and then lists the pack contents; no filler or redundancy. It is efficient, though the feature list is dense and could be structured more scannably.

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 a zero-parameter schema, an existing output schema, and annotations covering the safety profile, the description's main job is to convey scope and cost, both of which it does. The one remaining gap is relative positioning against the twelve sibling tools, which it never addresses.

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?

There are zero parameters, so the baseline is 4 and there is no schema-level parameter meaning to add or compensate for. The description correctly says nothing about inputs, which is appropriate here.

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 concrete deliverable ("Full machine-readable research pack") and enumerates its contents: expanded official evidence, global news, graph relationships, price lags, and commercial opportunity analysis. That is a specific resource description. It does not, however, differentiate this tool from the many similarly named siblings (e.g., shadowgraph_global_brief, shadowgraph_opportunity), so it lands at a clear-but-undifferentiated 4.

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 only usage-oriented signal is the price ("Paid ($5.00/call)"), which implies a cost tradeoff but never says when to choose this over shadowgraph_free_preview or the other briefs. No when-to-use, when-not-to-use, or alternative-naming is provided, so this is essentially absent guidance.

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 readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds only "Free" and the fact that notices are "current", with nothing on rate limits, auth, or result volume despite openWorldHint implying an external live source.

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 front-loads the cost cue and the core action with no filler. It is efficient, though its brevity borders on under-specification for a three-parameter search tool.

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?

An output schema exists, so return values need not be explained, and annotations cover the safety profile. Still, with 33% parameter coverage and no routing guidance among many sibling tools, the definition is minimal rather than 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 coverage is only 33%: country is documented in the schema, while keyword and limit have no descriptions. The description restates that keyword and buyer country act as search filters but adds no format, matching behavior, or meaning for limit (capped at 10), so the low-coverage gap is not compensated.

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 (current EU TED procurement notices) with the filtering dimensions (keyword, buyer country). It is clear on its own, but it never distinguishes itself from the closely related sibling shadowgraph_procurement_opportunity, so an agent must guess which procurement tool to pick.

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 "and/or" phrasing implies the two filters are optional and combinable, and "Free" hints at a cost boundary, but there is no explicit when-to-use, when-not-to-use, or named alternative against shadowgraph_procurement_opportunity. Usage 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?

Annotations already declare readOnly, idempotent, non-destructive, and open-world behavior, so the safety profile is covered. The description still adds real behavioral context: it is free (cost), "live" (freshness), and "compact" (payload size), which the annotations do not 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?

A single sentence with the differentiator ("Free") front-loaded and no filler. Every clause carries content or routing value.

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?

An output schema exists, so return values need not be spelled out, and the annotations cover safety. The description still tells the agent what the preview contains and what to do next, leaving little an agent needs missing for a zero-param read tool.

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 per the rubric the baseline is 4. The description correctly implies parameter-free invocation by describing a fixed preview payload.

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 ("Return") and enumerates concrete contents: global coverage, relationship graph, and top price-lag signal. It also implicitly positions itself as the free entry point versus the paid tools, though it never names a specific sibling, so differentiation is thematic rather than explicit.

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?

"Free" and "plus the paid tools to call next" imply this is a starting point that escalates to paid siblings, which is useful workflow guidance. However, there is no explicit when-to-use/when-not statement and no named alternative, so the agent must infer the routing.

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 (readOnly, idempotent, openWorld, non-destructive). The description adds a genuinely non-obvious behavioral trait: per-call cost of $2.50, which should make an agent think twice before invoking it. It does not describe latency or pagination, but with an output schema present the remaining burden is low.

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 cost signal, that wastes little space while packing in the content domains. The trailing enumeration is slightly list-like but each item earns its place by describing coverage.

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 an output schema to explain the return shape, the description only needs to convey scope and cost, which it does. The one real gap is differentiating this from the many similar shadowgraph siblings, which complexity here does not excuse.

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 and the baseline of 4 applies. No syntax, defaults, or format guidance is needed here.

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 resource (a global intelligence brief) and enumerates the data domains it fuses (official disclosures, EU procurement, news, relationship graph, lead/lag, opportunities), so an agent understands what it returns. However, it does not distinguish itself from close siblings such as shadowgraph_global_snapshot or shadowgraph_deep_research, leaving the 'brief vs snapshot' choice ambiguous.

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 'Paid ($2.50/call)' marker and 'Higher-density' phrasing imply this is a premium, heavier option to be used selectively rather than a default, which is useful implied guidance. But no sibling is named and there is no explicit when-to-use/when-not-to-use rule despite a shadowgraph_free_preview and several overlapping siblings existing.

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 readOnly, idempotent, non-destructive, and openWorld, so the safety profile is covered. The description adds 'Free' (cost) and characterizes the returned content, which is genuine extra context, but it omits rate limits, freshness/latency, and depth of 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?

Two short sentences with the cost tag and the core question front-loaded, then the return content. No filler, though the phrasing is slightly informal ('what moved').

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 an output schema present, the description need not document return values, and it correctly focuses on what the tool answers and roughly what comes back. The only gap is a missing distinction from the numerous sibling market-summary 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?

Schema coverage is 0% for the single 'limit' parameter, so the description should compensate. 'Returns the largest current company moves' loosely implies limit bounds the number of moves returned, but it never states the parameter's meaning or that it caps results at 10.

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 (answer/return) and resource (global market moves plus thematic news) with a clear temporal scope ('today'). It is distinguishable from siblings like global_snapshot or market_signal, though it never names or contrasts 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?

'Answer the concrete question: what moved in global markets today?' and the 'Free' tag imply the usage context (quick recap, cost-sensitive). There is no explicit when-to-use or when-not-to-use guidance relative to the many sibling brief/snapshot/signal tools.

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, idempotentHint, destructiveHint=false, and openWorldHint=false, so safety is covered structurally. The description adds genuinely new context: this tool is free and serves as the pricing/discovery surface for the paid tools, which is exactly the kind of cost/role information 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 dense fragments with zero waste. The cost signal ('Free.') is front-loaded before the payload description, which is the most decision-relevant fact for an agent choosing among paid siblings.

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 an output schema present, the return values (capabilities, prices, URLs) need not be spelled out in the description, and no parameters require explanation. What remains thin is routing guidance relative to the three sibling tools, which is the only real gap.

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 no per-parameter semantics to document and the baseline for a no-param tool is 4. The description does not need to compensate for any schema coverage gap here.

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 (Return) and enumerates concrete resources: service capabilities, paid-tool prices, and discovery URLs. An agent can tell this is the metadata/discovery entry point, though it doesn't explicitly name the sibling tools it complements.

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 leading 'Free.' plus the mention of 'paid-tool prices' implies this is the discovery call to make before/instead of the paid siblings, but there is no explicit when-to-use or when-not statement naming shadowgraph_alpha or the others.

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