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

Annotations already disclose the mutation profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so the bar is lower, yet the description still adds real value: it describes the shape of delivered matches (source URL, paragraph text, verification status) and the delivery semantics of each push kind. It does not state whether re-registering the same id updates or errors, which is the notable remaining gap for a non-idempotent tool.

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 with purpose and return shape, then a compact inventory of inputs. The second sentence is a long run-on parameter dump, but almost every clause carries information an agent needs, and nothing is wasted.

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 usefully describes what a match delivery contains and how it is pushed, which is the main completeness requirement here. The remaining gap is lifecycle behavior on duplicate ids and whether registration is persistent across sessions, minor against otherwise rich coverage.

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 only 50%, so the description has to compensate, and it largely does: it names id, connector_ids, query, jurisdiction, language, the three threshold kinds with a count for delta_at_least, the webhook URL with optional secret reference, and sse. It adds meaning beyond the enum values themselves, though it never explains what id represents or how it is used for later lookups.

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?

Specific verb+resource ('Register a sourced monitor') with an explicit statement of what comes back (the registered template). It is clearly distinguishable from siblings like monitor_list_templates, monitor_delete_template and monitor_register_connector, which the description implicitly contrasts by focusing on creating a watch plus a push.

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 implied rather than stated: calling connector_ids 'your registered connectors to watch' hints that monitor_register_connector must run first, and the push-mode options imply when to pick webhook vs sse. But there is no explicit when-to-use / when-not guidance, no note on what happens if the id already exists, and no routing to monitor_list_templates or monitor_delete_template.

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