ads_telegram_ai_keyword_observe

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

With no annotations, the description does real work: it discloses a write side effect (updating local trend counters), a privacy guarantee (submitted text is not stored), and a surprising non-behavior (never contacts Telegram). Missing disclosure of deduplication behavior or what happens on repeat submissions, but the key behavioral traits are covered.

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 compact sentences with the core action front-loaded and the caveats trailing. No filler, nothing repeated from the schema.

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?

The description explains the operation and its privacy/side-effect profile, which is the minimum for a 9-parameter local-write tool with no annotations and no output schema. It leaves the caller without guidance on the six undocumented parameters or on what the tool returns (e.g., extracted keywords), which is a meaningful gap given the complexity.

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 only 11% (just source_ref) across 9 parameters, so the description is expected to compensate and largely does not. It indirectly maps to text and source_type but says nothing about topic, intent, language, metadata, project_id, or observed_at, leaving most of the input contract undocumented.

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 (extract) plus resource (normalized demand keywords) and adds the side effect of updating local trend counters, so the tool is clearly distinguishable from read-only siblings like ads_telegram_ai_keyword_list or ads_telegram_ai_trend_snapshot_build. It stops short of naming a sibling alternative, so an agent must infer the boundary with ads_telegram_ai_keyword_rebuild.

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?

"from one search query or user-provided text" implies the single-item scope and suggests this is the ingest path rather than a bulk rebuild, but no explicit when-to-use/when-not or alternative tool is named. The Telegram disclaimer hints at what the tool is not for, but the routing decision against keyword_rebuild, keyword_list, and trend_snapshot_build is left implicit.

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