Monitor index build

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

The description discloses behavioral details beyond annotations: it explains the computed progress_pct logic (blocks first, tuples as fallback, null when no denominator) and that it returns one row per build. Annotations already declare readOnlyHint=true, and the description aligns with a read operation.

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?

The description is concise with four well-structured sentences. It front-loads the main purpose, details output fields, and adds usage guidance, with no unnecessary words.

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?

For a moderate-complexity monitoring tool, the description fully covers the return value semantics, including computed fields and edge cases (null progress). The output schema is described in detail, making the tool self-contained for an AI agent.

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% for the single parameter `database`, and the description does not add significant meaning beyond what the schema provides ('Optional: target a configured secondary database'). It meets the baseline for high coverage.

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 clearly states it surfaces active CREATE INDEX progress from pg_stat_progress_create_index, specifying the data source (PG12+, no extension) and output fields. It distinguishes itself from sibling tools like list_active_queries by mentioning when it's useful.

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 provides explicit when-to-use guidance: 'Useful next to list_active_queries when an HNSW / IVFFlat build on a big table is taking longer than expected.' This gives clear context, though it doesn't explicitly exclude alternatives or state prerequisites beyond the PG version requirement.

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