ScienceShot data-centre intelligence

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: the data is "dated" (a snapshot with a timestamp) and the grid carbon intensity / power price are "this hour" values, which tells the agent about freshness and temporal semantics.

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?

Well front-loaded: purpose first, usage examples second, accepted values last. The two long comma-separated value lists consume most of the length, but they carry real disambiguating information given the absence of schema enums, so the size is largely earned.

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 full burden of describing returns and does so thoroughly—it enumerates every category of output the agent can expect. Combined with annotations covering safety and a fully documented single parameter, nothing needed to invoke or interpret the call is missing.

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% and the single parameter is described with examples, so the baseline would be 3. The description goes beyond the schema by enumerating the full set of accepted metros (London, Frankfurt, Paris, Amsterdam, Dublin, Milan, Madrid) and 24 countries, effectively supplying the enum constraint the schema lacks.

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?

It names a specific resource (a European data-centre market snapshot) and enumerates the concrete facts returned: project counts ≥5 MW, permitted/building split, top developers, grid-connection posture, carbon intensity, power price, rule counts. That is far more than a restatement of the title. It stops short of 5 because it never contrasts itself against siblings like grid_carbon_and_price_now or data_centre_rules that cover overlapping slices.

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?

"Use for questions like 'data centres in Germany', 'Frankfurt data centre market'" gives the agent concrete trigger phrasings. However, there is no when-not guidance and no pointer to the alternative single-facet tools, so the agent must infer that this is the aggregate/market-wide choice rather than the per-topic ones.

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 the safety profile is covered. The description adds genuine behavioral value by disclosing the shape of the returned content ('each with its status, who it applies to and the next date that matters, plus upcoming deadlines'), 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?

Purpose is front-loaded in the first clause, followed by parenthetical detail and a country list. The long enumeration is verbose but justified as it defines valid inputs; otherwise the text is tight with 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?

With no output schema present, the description carries the burden of describing returns and does so adequately (status, applicability, next date, upcoming deadlines). For a single-parameter, read-only lookup the definition is nearly complete, missing only detail on output format/granularity.

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% and the schema already documents the single 'country' parameter. The description goes beyond it by enumerating the exact supported countries, effectively providing an enum-style constraint the schema lacks, which materially improves correct invocation.

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 resource (national and EU rules for building/running a data centre) with concrete content categories (energy efficiency reporting, waste heat, permitting, grid). This clearly distinguishes it from siblings like data_centre_market_overview and grid_connection_status, which cover market and grid data rather than regulatory rules.

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 phrase 'in one European country' and the enumerated country list imply a one-country-per-call usage model, which is useful context. However, there is no explicit when-to-use vs when-not-to-use guidance and no mention of alternatives (e.g., market overview for commercial data instead of rules).

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, destructiveHint=false and closed-world, so the safety profile is covered. The description adds real behavioral context the annotations lack: the fields returned, the cleanest-window and ranking behavior, and the time-sensitivity ('this hour's') that explains why an identical read is not idempotent. It does not discuss pagination or freshness lag, so not a 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?

Front-loads the payload (carbon, renewable share, price, window, rank) in the first sentence and defers the market enumeration to the end. The long market list is dense but earns its place since there is no enum in the schema. Slightly verbose overall, so not a 5.

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, so the description correctly carries the return-value burden by naming every returned field and the ranking/cleanest-window semantics. Combined with the covered annotations and the explicit enum-free market list, an agent has everything needed to invoke and interpret the 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?

With one optional parameter and 100% schema coverage, the baseline is 3. The description exceeds that by enumerating the 15 valid markets (Germany, United Kingdom, France, etc.), which the schema does not capture as an enum, directly resolving the main ambiguity about what values 'market' accepts.

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 concrete verb+resource: it returns this hour's grid carbon intensity (with unit gCO2/kWh), renewable share, day-ahead price, the cleanest window ahead, and market rank. The resource is clearly distinct from the siblings (data centre overview/rules, grid connection status, science search). An agent knows exactly what data this yields without opening the 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?

Gives explicit conditional behavior: with a market it returns that market's data; 'Without a market: all markets ranked cleanest first.' This tells the agent how to call it in both modes. It stops short of naming alternatives or exclusions, so it is clear context rather than full when/when-not 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 declare readOnly, idempotent and non-destructive, so safety is covered. The description adds value beyond them by describing what each result contains (measure name, scope of application, start date) and the geographic coverage, 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?

The scope statement is front-loaded and the trailing examples are compact and genuinely useful for routing. Slightly longer than necessary given the schema already documents the country default, but there is little waste.

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 one-parameter, read-only lookup with no output schema, the description covers coverage area, returned fields, default behavior and example intents. An agent has everything needed to invoke it correctly and interpret the result.

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% and the single optional parameter is fully documented there, including the same leave-out default the description restates. The description adds no new format or syntax detail, 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?

Names a specific resource (new grid connections for data centres in Europe) and enumerates the exact statuses returned (paused, rationed, conditional, congested) plus the fields attached to each measure. An agent can distinguish this from grid_carbon_and_price_now purely from the description.

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?

Two concrete sample questions anchor the intended use case and the description states the no-country default ('the whole ranking'). It does not name a sibling as the alternative or state when not to use it, so it falls short of 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?

Annotations already establish readOnly, idempotent, non-destructive and a closed corpus (openWorldHint=false). The description adds the genuinely non-obvious behavioral fact that results are capped at 5 pages and that each result carries title, date, link and summary, which annotations cannot express.

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 filler: the corpus scope comes first and the result shape second. Every clause carries information an agent can act on.

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 one-parameter search with no output schema, the description covers the corpus, the hard result cap and the return fields, so an agent can call and interpret it. It stops short of explaining ranking or how to retrieve results beyond the first five.

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 single query parameter is documented in the schema with concrete examples ('PUE benchmarks', 'fibre latency London Frankfurt'). The description adds no syntax, quoting or format guidance beyond that, so the 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?

The description names a specific verb (search) and a scoped resource (ScienceShot's trackers, reference pages, articles) and even enumerates the topical domains covered. That makes it immediately distinguishable from siblings like data_centre_market_overview or grid_connection_status, which are specific lookups rather than general search.

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 fallback for free-text discovery when no specific sibling lookup applies, but the description never states that. There are no when-not conditions or explicit routing to the sibling tools.

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