get_instructions

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

With no annotations, the description carries the behavioral burden itself, and it does state what comes back (instructions verbatim plus live upstream status) and when the result is worth refreshing. It stops short of describing output format, size, or whether the upstream status check has any cost/latency, so it is not fully rich, but it is well beyond a bare restatement.

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, zero filler, and correctly front-loaded: the what comes first, the when second. Every clause earns its place and nothing redundant is repeated from structured fields.

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 zero-parameter, no-output-schema tool, the description covers everything an agent needs: what is returned, that the return includes live state, and the two situations that warrant calling it. No meaningful gap remains for correct invocation.

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 there is nothing to document and the baseline for empty parameter sets applies. The description correctly implies a no-argument call by never referencing any input.

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 ('Return the operating instructions for this bridge verbatim') and adds the secondary payload ('live status of attached upstream MCP servers'). This is unambiguous and easily distinguished from the filesystem-ish siblings (read, ls, grep, find, bash) since none of them retrieve bridge instructions.

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 call timing: 'once at the start of a session' and again 'when a tool you expect is missing or an upstream is reported unavailable.' This is a rare case where both the when-to-use and the re-invocation trigger are spelled out, leaving nothing to inference.

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