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

The annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds the upstream source (CelesTrak SOCRATES) and a 7-day lookahead window, which is genuinely useful context, but it says nothing about rate limits, freshness, or how an empty result is returned.

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 that leads with the predicted-approach scope and adds only clauses that earn their place. The semicolon-joined second clause is dense, but nothing is redundant or restated from the name or title.

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 4-parameter, zero-required tool with no output schema and no per-parameter documentation anywhere, the description covers the filter and sort dimensions adequately but omits the result-limit parameter ('max', 1–50), default behavior, and any sense of the response shape.

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 carries the full burden. It decodes the cryptic ORDER enum values into human terms (max probability, miss distance, time) and clarifies that name is a pattern (e.g. STARLINK, ISS) rather than an exact match. It leaves the 'max' parameter completely unexplained, which caps it below 5.

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 ('Predicted close approaches'), plus the source (CelesTrak SOCRATES) and the temporal window (next 7 days). It is unambiguous on its own, though it never names a sibling (satellite_info, track_group, space_weather_*) to distinguish itself from them.

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 description enumerates the three selectable scopes (NORAD id, name pattern, or overall), which implies how to call it, but it gives no explicit when-to-use guidance, no indication of when to prefer a sibling tool, and no statement about which filters can be combined.

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 (readOnlyHint=true, openWorldHint=true), so the bar is lower, and the description still adds real value by enumerating the returned payload (owner, launch, status, decay, current orbit, live position). It does not mention rate limits, error behavior for unmatched names, or how 'live position' is sourced, but the return-content disclosure goes meaningfully beyond annotations.

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: verb, object classes, source catalog, accepted identifiers, and returned fields, in that order. Every clause earns its place and nothing is repeated from the schema or annotations.

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 3-parameter, no-output-schema lookup tool, the description covers what it queries, the keys it accepts, and the fields it returns. The one remaining gap is disambiguation policy (e.g., ambiguous name matches, precedence among the three keys), but overall an agent has enough to call it correctly.

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% (only intlDes is documented in the schema), so the description has to carry weight, and it does map the three accepted lookup keys to the three parameters. However, it never clarifies that the parameters are alternatives (0 required) or what happens if multiple are supplied and conflict, which is the main semantic ambiguity an agent faces 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 (look up) and resource (any tracked object in the CelesTrak SATCAT) and enumerates the accepted lookup keys (NORAD id, name, international designator). This is clearly distinguishable from siblings like track_group or conjunctions, which operate on collections or events rather than a single catalog object. The object classes (satellite, rocket body, debris) further sharpen scope.

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 lookup framing rather than stated: an agent can infer this is the per-object catalog query, but the description never says when to choose it over track_group or conjunctions, nor does it give any prerequisites or exclusions. No alternatives are named. Adequate but with a clear routing gap.

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=true, so safety and external-dependency behavior are covered. The description adds genuine content context (the alert categories and that stated impacts are included), but says nothing about the default time window, ordering, or result volume, which matters for a feed-style 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?

A single front-loaded sentence with no filler; the alert types are parenthetically grouped rather than padded. It is well sized, though it could have spent a few extra words on the time-window parameter instead of listing event types.

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 and zero parameter documentation, the description carries the burden for explaining the return shape and the meaning of hours/limit, and it does neither. An agent can identify the tool but cannot confidently scope a call.

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 the two parameters (hours, limit) and the description never mentions either. 'Recent' only loosely hints at the hours window and gives no clue about the limit parameter, so the description fails to compensate for the schema 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 names a concrete resource (NOAA SWPC alerts, warnings and watches) and enumerates the event types it covers (geomagnetic storms, flares, proton events), so the agent knows exactly what entity is returned. It does not, however, contrast itself with the sibling space_weather_now, so differentiation is left to inference.

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 statement of when to use this tool versus space_weather_now or the other siblings, no mention of defaults, and no indication of how far back 'recent' reaches. The agent must guess whether this is a historical-feed tool or a current-conditions 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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety and external-data scope are covered. The description usefully adds the data payload scope and a plain-English impact framing (GPS, HF radio, Starlink/LEO, aurora). It does not disclose update cadence, caching/freshness, or whether NOAA may be unreachable, which matter for a 'now' 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?

A single front-loaded sentence that identifies the source and enumerates contents with no filler. The enumeration is dense but each item is genuinely informative about what comes back, so it earns its length.

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, no output schema, and annotations covering the safety profile, the description's main remaining job is to say what the response contains – which it does thoroughly. It is essentially complete; cadence and format are the only untold pieces.

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 schema is empty and nothing in the description could or should add parameter meaning.

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 (current NOAA space weather) and enumerates the exact content: G/R/S scales, planetary Kp, flares, 3-day outlook. That is far more than a restatement of the title. It stops short of explicitly differentiating itself from the sibling space_weather_alerts, which is the one tool an agent could easily confuse it with.

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 word "Current" plus "3-day outlook" implies this is the snapshot/status tool rather than an alert-subscription tool, so usage is inferable. However, there is no explicit when-to-use, when-not-to-use, or named alternative (e.g. 'for active alerts, use space_weather_alerts'), which is exactly the ambiguity a sibling named space_weather_alerts creates.

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=true, so safety is covered. The description adds substantive behavioral content beyond that: it states the tool aggregates counts and characterises objects, and that results are expressed as altitude bands and orbital regimes — meaningful since no output schema exists. It stops short of data-freshness or external-call behavior implied by openWorldHint.

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 that leads with the verb and packs the input domains and the return characterisation into one pass. Slightly dense and colon-appended rather than cleanly structured, but no filler sentences.

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 2-parameter, no-output-schema, read-only tool the description covers purpose, input values and result shape well. The notable gap is that both parameters are optional with no stated default: an agent cannot tell what a call with no arguments returns, nor whether group and debrisEvent are mutually exclusive. Source/freshness of CelesTrak GP data is also unstated.

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 carry the load and largely does: it names the debrisEvent enum members and gives multiple valid `group` values that the bare regex pattern (^[a-z0-9-]{2,40}$) cannot convey. It does not clarify that the two parameters are alternative selector modes or whether both may be supplied at once.

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?

Specific verb pair plus resource: 'Count and characterise objects still in orbit' for a named debris event or CelesTrak GP group. It clearly distinguishes the tool's scope from siblings like satellite_info (single object) or conjunctions (pairwise events), though it never explicitly names an alternative. No schema opening is needed to know what it does.

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 supplies the concrete trigger conditions and enumerates usable input domains ('cosmos-1408, fengyun-1c...' or 'starlink, stations, gps-ops, oneweb, last-30-days'). What it omits is any exclusion or routing rule — e.g. when to prefer satellite_info or conjunctions, or whether the two parameter families can be combined.

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