list_ip_services

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

Annotations already declare readOnlyHint/idempotentHint, so the safety profile is covered. The description adds genuinely useful behavioral context: filtering semantics ('substring match'), what `enabled_only` suppresses, and that an empty address plus a public WAN means internet exposure. It stops short of pagination/ordering behavior but adds real value beyond the annotations.

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 one-line purpose followed by scoped notes on filtering and interpretation. The SFTP-vs-ftp aside is slightly tangential but tied to the tool's security-audit value, so it earns its place; overall it is efficient, if a touch prose-heavy.

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?

An output schema exists, so return values need not be restated, and the description sensibly focuses on how to read the returned address/port fields. Combined with the parameter notes, it gives an agent enough to call and interpret the tool; only the `device` argument lacks any explanation.

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 0%, so the description carries the load and largely does: `name_filter` is documented as a substring match with concrete examples and `enabled_only` is explained as hiding disabled entries. Only the `device` selector is left undocumented, a minor gap given the rest is well covered.

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+resource: 'Lists the management services with their port and address restriction.' An agent immediately knows this enumerates RouterOS IP services (winbox/ssh/api/www/etc.). It does not name or distinguish against a sibling, but no sibling covers the same resource, so the risk of confusion is low.

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: the notes on `enabled_only=True` being 'the list that actually describes exposure' and the WAN/unrestricted-service discussion suggest this is an exposure-audit tool. There is no explicit 'use this when... / use X instead' routing or prerequisite, so guidance is only inferable.

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