get_upstream_status

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely non-obvious behavior: the tool never probes proactively, status derives from passive registry state during normal calls plus bootstrap-declared static state. It also enumerates the status values and the per-entry fields, which is exactly the context needed to interpret 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?

Front-loaded purpose sentence, then the field inventory, then the behavioral caveat and the when-to-call guidance — a good order. Slightly over-long: the source-module reference (`_shared/health.py`) and the full parenthetical enum listing are implementation detail an agent does not need to act.

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 no-arg, read-only introspection tool with an output schema, this covers everything an agent needs: what it reports, how the data is produced, the latency/accuracy caveat (passive, not live), and when to consult it before downstream calls.

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?

There are zero parameters, so the baseline is 4; nothing about invocation needs explaining. The description instead spends its words on the return shape, which is a sensible use of space but not parameter semantics.

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?

Opens with a specific verb+resource ('Return the current health of every registered upstream endpoint') and immediately establishes scope ('every'). It is clearly distinguishable from sibling status tools like get_knowledge_status and list_features because it is about upstream endpoint health, not knowledge coverage or feature inventory.

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?

Explicitly tells the agent when to call it: before attempting Tier 1 (Dubai Pulse) or FCSC work, with the rationale (avoiding requests the server cannot fulfill). It does not, however, exclude any situations or contrast itself against the other meta-tools (recommend_tools, get_knowledge_status) that an agent might also consult first.

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