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

Annotations only declare the read-only, idempotent, closed-world profile; the description goes well beyond that by disclosing the grouping (by account, newest first), per-alert fields, the state filtering semantics including what 'open' excludes, the meaning of 'origin baseline' as non-news, the distinction between new_alerts and new_alerts_total, the MCP-specific default of 5 accounts versus the schema's 20, and the has_more signal. These are exactly the operational traits an agent cannot get from 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?

It is front-loaded with the use case and then the return shape, and virtually every clause carries information. Some sentences are telegraphic ('state open, the default, leaves out dismissed alerts. origin baseline predates monitoring, so it is not news.'), which is dense but slightly harder to parse than fully formed sentences.

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?

There is no output schema, so the description deliberately supplies the return shape (grouped by account, newest first, headline/dates/state/source links) plus count semantics and the has_more expansion hint. Combined with the watching prerequisite and pagination guidance, nothing essential for a correct first call is missing.

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?

Reported schema coverage is 0% (only the nested 'query' wrapper is described at top level), so the description must carry the load; it does explain state defaults and exclusions, the effective MCP limit of 5 versus the declared default, and the enum values of signal_type indirectly through the alert-type list. It does not explain the company substring filter or company_card_id's link to getPipeline, leaving those to the schema alone.

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 names a specific resource (buying-intent alerts on watched pipeline accounts) and enumerates what they cover (funding, new jobs, product and leadership news, contacts' job changes). It is clearly distinguishable from siblings like getAccountWatch, markSignals, and watchAccounts, which deal with watch configuration or alert state rather than listing alerts.

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?

It gives a concrete trigger ('when the user asks what changed at their accounts or who to contact now'), which is more than implied usage. It also notes that accounts are watched from the Leadpoet app or via watchAccounts, implicitly routing the agent there when nothing is watched, but it never states when to prefer markSignals or getAccountWatch instead, so there is no explicit exclusion guidance.

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