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

Beyond the annotations (readOnlyHint, idempotentHint, openWorldHint), the description discloses three non-obvious behaviors that an agent cannot infer from the schema: the ~30-day rolling retention with data vanishing afterward, the timezone ambiguity resolved by 'Tbilisi local time (UTC+4) unless timezone is set to utc', and the strict failure mode — 'reports the miss rather than substituting a nearby one'. The last trait is especially valuable because it tells the agent not to silently trust a nearest-neighbor result.

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?

Four sentences, each load-bearing and ordered for impact: purpose/scope first, then source plus retention, then timezone semantics, then failure behavior. No filler, no repetition of schema content, and the densest information (the data blocks and the gse_grid_now relationship) is front-loaded.

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?

Even without an output schema, the description signals return content ('generation, tie-line and consumption blocks', 'QUALITY flags'). The edge cases an agent would otherwise stumble on — expired timestamps, timezone ambiguity, and unpublished slots — are all addressed. For a 2-parameter, read-only, idempotent lookup, nothing critical 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?

Schema description coverage is 100%: both timezone and timestamp already have descriptive schema text covering enum values, the 'tbilisi' default, accepted formats, and flooring to the 3-minute grid. The main description adds only reinforcing context (the concrete UTC+4 offset and the slot granularity), which is useful but does not meaningfully expand on the schema — placing it at the baseline for well-covered schemas.

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 ('Georgia's national grid state'), the time scope ('a specific past time', 'one 3-minute slot'), and the payload ('generation, tie-line and consumption blocks' with 'QUALITY flags'). The explicit comparison to gse_grid_now distinguishes it from its closest sibling, making it the historical counterpart of the live-state tool rather than a vague grid-data getter.

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 establishes clear usage context: reading a past 3-minute slot of grid state, with the rolling ~30-day retention window bounding data availability ('earlier timestamps are gone'). It references gse_grid_now as the live analogue, but never bluntly states 'use gse_grid_now for current state' and doesn't name other sibling data tools (e.g., gse_frequency, gse_demand_forecast) as alternatives for different data types, so selection logic is partially implicit.

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