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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds useful behavioral details beyond that: the mark_read flag's side effect on future calls ('so the next call only shows newer ones') and the return payload composition ('each carries source, citation_uri, and the raw event payload'). It does not contradict any annotation and provides meaningful context.

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?

The description is three sentences long and front-loads the core purpose. Every sentence adds value: purpose, return format/filter/mark_read behavior, and polling/alternative endpoint note. No filler or repetition.

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 compensates by explaining the return payload at a high level. It covers usage patterns (filters, mark_read), polling suitability, and an external reference for integration. The tool is simple and the description is complete for the given context.

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?

The input schema already documents all 5 parameters with 100% coverage, so the baseline is 3. The description adds value by giving a concrete filter example ('e.g. "sec_8k"'), clarifying the 'since' parameter as an ISO timestamp, and explaining the consequence of mark_read in operational terms. This goes slightly beyond the repetitive schema descriptions.

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 uses a specific verb+resource construction ('Pull fired events from your subscription feed') and clearly identifies the tool's output ('Returns the most recent alerts the evaluator has written to your persisted feed'). It distinguishes itself from siblings like 'recent_changes' by explicitly focusing on alert events from the subscription feed.

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 description gives clear context that this tool is suitable for polling ('Polls work fine') and provides an explicit alternative for scripts/dashboards via a direct HTTP endpoint ('the same feed is also at GET registry.pipeworx.io/alerts.json'). It does not explicitly state when not to use the tool, but the context is sufficient.

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