Get an artifact

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description is consistent with a safe local read. It adds genuinely useful behavior beyond the annotations: inline text truncation over 1 MB (head, or tail for logs), binaries returning metadata instead, and image downscaling to JPEG at 1568 px long edge. However it omits error behavior for a bad URI and any inline size caps, so it adds context without a full behavioral picture.

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?

Three tight sentences, front-loaded with the core action and URI form, then scope condition, then return behavior. The compression in "Binaries return metadata; mode:\"inline\" returns the bytes" makes the contrast slightly harder to parse than it needs to be, but nothing is padded.

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 correctly takes on return-value description: inline text vs metadata for binaries, truncation rules, and image format/resize. Enough to call it correctly and predict the response shape. Missing only edge-case behavior such as unknown URI handling and any size limit on inline mode.

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 entire burden, and it does real work: it gives the uri template swipium://session/<id>/<kind>/<name> and explains what each mode value actually yields (metadata stub vs raw bytes). It never states the default mode when omitted, leaving one operational 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?

States a concrete verb and resource ("Fetch a session artifact") and enumerates the artifact kinds plus the exact URI shape it accepts, so the agent knows precisely what comes back. It does not name or contrast with the sibling qa_resolve_artifact, which is the one nearby ambiguity an agent could hit, 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 condition "when the client lacks MCP resources" is an explicit when-to-use trigger that an agent can actually test against context. It also implicitly guides mode choice by pairing metadata with binaries and inline with byte retrieval. No explicit when-not or named alternative, which keeps it at 4.

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