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

Annotations already declare non-read-only, open-world, non-idempotent, non-destructive, so the safety profile is covered. The description adds two genuine behavioral facts: the tool returns the registered connector, and monitor runs over connectors carry no per-run token charge. It does not disclose what happens on a duplicate id (a real concern given idempotentHint=false) or what errors/validation occur.

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?

Purpose is front-loaded in the first clause, and the rest is a compact enumeration of inputs plus two closing facts. The single long run-on 'Inputs: ...' sentence is dense but every element carries information and 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?

For an 8-parameter mutation tool with no output schema, the description covers inputs, enum semantics, auth expectations, the return value, and a billing note. The remaining gap is failure behavior (duplicate id, invalid endpoint), which an agent would need to anticipate.

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 100%, so the baseline is 3, but the description earns above baseline by explaining the 'kind' enum far more richly than the schema (e.g. 'https_json' answers JSON with url plus text, paragraph_text or title; 'pauhu_sources' covers your plan's sources) and by tying auth_kind='bearer' to a stored token reference. The mcp_tool_name default and poll_fallback_secs description largely duplicate the schema.

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 states a specific verb and resource ('Register one of your APIs or MCP servers as a connector') and frames the purpose ('so your sourced monitors can watch it'), which clearly distinguishes it from monitor_list_connectors and monitor_delete_connector by role. It stops short of explicitly naming any sibling as an alternative or complement.

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 only implied: 'so your sourced monitors can watch it' suggests you register before monitors can poll your own sources. There is no explicit when-to-use, no exclusion, and notably no routing between this and monitor_register_template, which is a plausible point of confusion among the siblings.

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