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

Annotations declare readOnlyHint and openWorldHint, so safety is covered. The description adds that it targets the single very next launch and that 'UTC always shown too' appears in the schema rather than here; it doesn't describe auth, rate limits, or return shape. With annotations carrying the safety profile, 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?

A single compact sentence that front-loads the primary function and appends the optional filter with concrete examples. Nothing 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?

For a two-param read tool with no output schema, the description covers purpose and filtering but leaves sibling differentiation and the search parameter's semantics thin. Adequate but with clear gaps relative to the sibling tool set.

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%: tz is documented in the schema, search is not (only maxLength). The description's filter examples ('Starship', 'Rocket Lab') add useful meaning for search but don't fully compensate for the undocumented parameter. 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?

Clear verb-like resource ('next launch') and stated scope ('countdown and details'), with the filter examples grounding what the tool returns. It doesn't explicitly distinguish itself from the sibling 'upcoming_launches', 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?

The 'optionally filtered' phrasing and examples imply when to pass a filter, but there's no guidance on when to use this versus 'upcoming_launches', which is the obvious alternative. Usage context is implied, not stated.

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 the safety profile (readOnlyHint, openWorldHint), and the description adds meaningful context beyond them: the naked-eye visibility criterion (satellite sunlit, sky dark) and the CelesTrak TLE + SGP4 data/model provenance. It still omits rate limits, TLE freshness, and failure modes, 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?

Two dense sentences front-loaded with the primary capability, targets, visibility semantics, and data source. No filler; every clause earns its place.

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 10-parameter tool with 50% schema coverage and no output schema, the description adequately covers purpose and the main input concept but leaves the time-range and elevation parameters unexplained. An agent has enough to call it, but not enough to use the optional parameters confidently.

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 50%, and the description adds meaning mainly for the satellite/noradId fields (naming conventions and default) and implies the visibleOnly behavior. Time-window (hours, start), altitudeM, and minElevationDeg remain undocumented in both schema and description, so it 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 specific verb+resource ('Predict passes') and enumerates the supported targets (ISS default, Tiangong, Hubble, or any satellite by name/NORAD id). An agent can grasp the tool's scope quickly, though it does not explicitly differentiate from the sibling starlink_passes despite overlapping function.

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 (predict passes over a lat/lon location, ISS as default). There is no explicit when-to-use/when-not guidance, and it does not route the agent toward starlink_passes for Starlink-specific queries, leaving sibling selection 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 only cover readOnlyHint and openWorldHint, so the description carries the rest and does disclose meaningful behavior: the default scope (6 most recent launches, the bright low trains) and hard caps (up to 3000 satellites, max 6 h). It stops short of describing result shape or empty/failure behavior.

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 sentences with no filler, and the core purpose is front-loaded before the mode/default behavior. Slightly compressed but every clause carries 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?

With 9 parameters, no output schema, and low schema coverage, the definition is only adequate: it omits what the start date-time does relative to hours, how minElevationDeg and maxResults shape results, and what a returned pass looks like. It is callable but an agent would guess at several knobs.

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 only 33% (tz, lat, lon), so the description must compensate, and it does add real semantics for 'mode' (bright low trains vs the full 3000-satellite sweep) plus the effective time cap for that mode. However, start, altitudeM, maxResults, and minElevationDeg remain unexplained in both the schema and the description.

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 and outcome ('Visible Starlink passes and trains over a location'), which is clearly narrower than the generic sibling satellite_passes. It does not explicitly name or contrast with that sibling, so it stops 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?

The description explains default versus 'mode: all' behavior, which implicitly tells the agent when each mode is appropriate, but it offers no explicit when-to-use guidance relative to satellite_passes or other siblings, nor any exclusions.

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 sourcing are covered. The description adds no behavioral context beyond that: no mention of caching, freshness, rate limits, or the shape of the countdown/outcome data. With annotations doing the safety work, this leaves little added value.

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 listing exactly what is returned, with no filler. Every clause earns its place.

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 aggregator with two parameters, no output schema, and sibling launch tools, the description is too thin. It never resolves the overlap with upcoming_launches/next_launch and never covers the newsLimit parameter, leaving the agent to guess scope and limits.

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%: tz is fully described in the schema, but newsLimit has only type/bounds. The description does not mention either parameter, so it fails to compensate for the undocumented newsLimit parameter. Baseline 3 applies given partial 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?

The description names the resource (SpaceX Starship) and states three concrete outputs: upcoming flights with countdowns, recent outcomes, and news headlines. It is specific about scope but does not differentiate itself from siblings like upcoming_launches or next_launch, which likely overlap in launch-listing behavior.

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?

Implicit usage is clear from the content (Starship-specific status), but the description never says when to pick this over upcoming_launches or next_launch, or whether it is Starship-only vs. all launches. No exclusions or alternatives are named.

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 this a safe read-only, open-world operation, so the burden is lower. The description adds useful context — the upstream source (Launch Library 2) and the live countdown/status fields returned — but says nothing about pagination, the 25-item cap, or how includeRecent changes 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 tight sentences, front-loaded with the purpose and data source, with no filler. Slightly dense, but every clause carries 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?

For a simple read-only list tool with no output schema, the description covers what is returned and where it comes from. It is still missing the behavior of includeRecent, the default/max for limit, and any note on result ordering or pagination.

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 25% (just tz documented), so the description must compensate. It adds examples for the search parameter ('SpaceX', 'Falcon 9', 'Artemis', 'ISRO'), which is helpful, but limit and includeRecent remain completely undocumented in both schema and description.

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 gives a specific verb+resource ('Upcoming orbital launches worldwide') and enumerates the returned fields (countdowns, provider, rocket, pad, status) plus the data source (Launch Library 2). It is clearly distinct from starship_status and satellite_passes, but the plural-vs-singular distinction from the sibling next_launch is left implicit 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?

There is no explicit when-to-use guidance or routing advice. The 'Optional search' sentence describes how to invoke the tool, not when to choose it over next_launch, and no exclusions or prerequisites are given.

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