watch_log_poll

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds real context beyond them: it discloses the cursor-based polling model and the full shape of each returned event (seq, kind taxonomy, time, script, message, frames, source with mod/draft-cache/file/line/excerpt). With no output schema, this return-value disclosure is valuable, though it omits trimming/pagination behavior.

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?

Two dense, front-loaded sentences with no filler; the core semantics (what is returned and the cursor contract) come first. The event-field list is long but earns its place since no output schema exists.

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 two-parameter polling tool with no output schema, the description covers the cursor contract and event payload reasonably well. It falls short on limit semantics and on any statement of polling behavior (blocking, empty-result handling), which an agent calling this in a loop would want.

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 must carry the burden. It explains since_seq ('new watcher events after since_seq', feeding next_seq forward), which is the critical parameter. But limit is never mentioned, leaving one of two parameters undocumented in both schema and description.

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 and resource: returns new watcher events after a cursor sequence. It clearly differentiates itself from watch_log_start/stop by being the read/poll side, though it doesn't name siblings explicitly. The event-kind enumeration reinforces what kind of output to expect.

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 parenthetical 'use next_seq from the previous call' is genuine usage guidance for continuing a polling loop. However, it gives no guidance on when to use this versus log_tail, read_log, or log_errors, and no mention of how limit interacts with polling.

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