Export post insights to CSV

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

Annotations declare a non-destructive write, and the description adds genuinely useful behavior beyond them: output location (data folder's exports/), that bare filenames land there too, that other paths require user approval, and that existing files are never clobbered thanks to a -1, -2 suffix. The one gap is what the tool returns (presumably the written path), which matters for a write operation. Minor tension worth noting: the collision-suffix behavior means repeat calls create additional files, which sits awkwardly with idempotentHint=true, though it is consistent with destructiveHint=false.

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?

Front-loaded with the action and artifact, then constraints in descending order of importance. The long parenthetical column list is bulky but pays for itself by telling the agent what fields the export contains. Sentence structure is dense but not padded.

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 should say what a successful call returns (file path? row count?), and it does not. The confirmation_token flow is left entirely to the schema. For a 6-parameter write tool whose primary result is an unseen file, that leaves the agent guessing about the response.

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 67%, and the description usefully reinforces path semantics (bare name vs. absolute/~ path needing approval) and enumerates the CSV columns, telling the agent what data the export carries. But since and until have no schema description and get no explanation in the description either, so date format and defaults remain unknown. Baseline 3 fits.

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?

Opens with a specific verb and artifact: 'Writes a CSV (one row per post: date, type, link, ... views, reach, likes...)'. An agent immediately knows this produces a per-post metrics export rather than returning data inline. It stops short of naming a sibling, so an agent must still infer that this is the file-export counterpart to get_media_insights or analyze_post.

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 phrase 'for spreadsheets' signals the intended consumption scenario, and the description explains where the file goes and when approval is needed. However, it never states when to choose this over get_media_insights or analyze_post, nor what happens if limit exceeds available posts. Usage is implied rather than directed.

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