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

Goes well past readOnlyHint: caps output at max 3/day, one line each with project tags, guarantees no repeats (dedup), defines the empty result as '{new:0}', imposes a daily call frequency, and asserts 'Never affects other tools.' These are exactly the operational traits an agent needs and can't get from 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?

Front-loaded with 'Daily feed' and every clause carries distinct information; there is no filler. The trade-off is extreme compression — notations like '{new:0} = nothing' take a moment to parse, which slightly hurts legibility.

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 still conveys return shape (one line per item, project-tagged, empty sentinel) and mode semantics, which is most of what an agent needs. The undefined 'limit' parameter and absent error/edge-case behavior are the remaining gaps.

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 load. It does define key (stateful saved-project mode) and since/interests (stateless mode), but the 'limit' integer parameter is never mentioned or bounded, and no value formats are given for since or interests.

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?

Names the resource and behavior concretely: a daily feed of 'new items relevant to ANY of the person's saved projects', one line each, tagged with the project. An agent understands what comes back. It does not, however, differentiate itself from siblings like search or recommend_tools, so it stops short of a 5.

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?

Explicitly splits the two modes: with a key it returns saved-project items, without a key it is 'stateless by since/interests.' It also states a cadence constraint ('Call at most daily'). It never names an alternative sibling for ad-hoc lookups, so no exclusions are given.

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