Skip to main content
Glama

Nasa

by io.github.pipeworx-io

Get Mars Photos

get_mars_photos
Read-onlyIdempotent

"Show me photos from the Mars rover" / "Perseverance images from sol 1000" / "latest pictures from Mars" — raw images from NASA's Perseverance rover (Mars 2020), straight off the mars.nasa.gov feed. Filter by Martian sol and by camera. Returns image URLs at four resolutions, the sol, the UTC and Mars-local capture times, and the camera instrument. Keyless. Covers Perseverance only — Curiosity, Opportunity and Spirit have no live public image feed. Example: get_mars_photos({ sol: 1000, camera: "NAVCAM_LEFT" })

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
solNoMartian sol (mission day) to retrieve images from, e.g. 1000. Perseverance landed on sol 0 (2021-02-18) and is past sol 1900. Omit for the most recent images.
limitNoMax images to return (default 20, max 100).
cameraNoCamera instrument, exact: "NAVCAM_LEFT", "NAVCAM_RIGHT", "FRONT_HAZCAM_LEFT_A", "FRONT_HAZCAM_RIGHT_A", "REAR_HAZCAM_LEFT", "REAR_HAZCAM_RIGHT", "MCZ_LEFT"/"MCZ_RIGHT" (Mastcam-Z), "SHERLOC_WATSON", "SUPERCAM_RMI", "SKYCAM", "PIXL_MCC", "CACHECAM". Short forms FHAZ/RHAZ/NAVCAM/MAST are accepted. Optional.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
solNo
countNoTotal number of photos retrieved
roverNo
cameraNo
photosNoList of Mars rover photos (up to 20)
total_matchingNo

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already indicate read-only, open-world, idempotent, non-destructive. Description adds keyless access, image resolution details, and capture time fields, enriching the behavioral context without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with query examples, but slightly verbose. Every sentence adds value, though a minor trim could improve conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a query tool with an output schema, the description fully covers input, constraints, and examples. No missing context for an agent to invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and description adds context like default limit, short forms for cameras, and explanation of sol meaning. Examples further clarify usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves raw images from NASA's Perseverance rover with filtering by sol and camera. It distinguishes itself from siblings like search_nasa_images by specifying it covers only Perseverance.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit query examples and guidance on when to omit parameters. Explicitly excludes other rovers (Curiosity, Opportunity, Spirit), telling the agent when not to use this tool.

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

All Nasa toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation2/5

Several tool clusters overlap heavily: ask_pipeworx, ask_pipeworx_beta (currently identical), and ask_pipeworx_grounded are three variants of the same router, while bet_research, polymarket_edges, and polymarket_arbitrage all target prediction-market opportunities. The descriptions are detailed, but an agent must read extensively to avoid selecting the wrong tool within each cluster.

Naming Consistency2/5

Naming is a mix of conventions: get_*/search_* for NASA tools, ask_pipeworx_* and polymarket_* family prefixes, plus one-off names like entity_profile, bet_research, deep_research, recent_changes, and scan_dependency. There is no consistent verb_noun or family-wide pattern, making tool selection unpredictable despite each individual name being readable.

Tool Count2/5

36 tools is heavy for a server named Nasa, and only 5 of them are actually NASA-related; the rest form a sprawling general data-research, prediction-market, memory, and subscription toolkit. The count is borderline defensible for a broad data assistant, but it is clearly unjustified under the server's stated NASA identity.

Completeness3/5

As a general data-research assistant the surface is quite complete: discovery, routing, grounded verification, entity profiles, comparisons, memory, subscriptions, and feedback are all covered. As a NASA server, however, there are notable gaps—no EONET events, Earth observation, exoplanet archive, or TLE/mission-specific data—and the large non-NASA tool surface does not fill those gaps.

Resources