get_syslog

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

No annotations exist, so the description carries the full burden; it does disclose the return ordering and record fields, which is real value. However, it says nothing about retention window, maximum limit, or whether results are paginated/truncated — for a log-dump tool with a default limit of 100, those are material operational traits left unstated.

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?

Three tight sentences: return shape and ordering first, then what it reveals, then how to filter. No filler, and the most load-bearing information is front-loaded.

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 needn't be spelled out, yet the description still gives the record shape, which helps. The gaps are the undocumented limit semantics and the unspecified log_type vocabulary; everything needed to make a first correct call is otherwise present.

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 0%, so the description must compensate, and it partly does: it supplies the accepted level values (INFO/WARNING/ERROR) that the schema leaves as an unconstrained string. But log_type is deferred externally ("see the router's categories") with no enumeration, and the limit parameter with its default of 100 is never mentioned at all.

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 resource (system log) plus the exact record shape [{time, level, type, content}] and ordering (newest first), so an agent knows precisely what it gets back. It also names the concrete event classes it surfaces (DHCP DECLINE loops, SAE/WPA handshake failures, DFS radar, session kicks), which clearly separates it from siblings like router_status or session_info.

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?

The enumerated symptom types (handshake failures, DFS radar events, session kicks) give concrete diagnostic triggers for reaching for this tool rather than a status endpoint. It stops short of naming an alternative or stating exclusions, so it is clear context without routing rules.

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