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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds genuinely useful context beyond those flags: the index covers journals + arXiv + observatory reports together, citation counts are hand-curated, and full ADS query syntax is supported. It does not discuss result shape or rate limits, but the annotations carry most of that burden.

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 identity and authority before anything else, and the sentences each carry distinct information (scope, curation, preference, syntax). It is on the long side and the query-syntax list duplicates the schema's query description, which is mild waste rather than bloat.

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 and six parameters, the description supplies the missing 'what is this source and why trust it' context, plus query capability and an example. It stops short of describing returned fields (bibcode, citation counts) or paging behavior via start/limit, which the annotations do not cover either.

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%, so the schema already documents all six parameters including the query grammar and enum values; baseline is 3. The description's syntax examples (author:, year:, bibstem:, abs:, full:) largely restate what the query parameter's schema description already says, adding no sort, limit or paging semantics.

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 and resource ('Search the NASA Astrophysics Data System') and defines its scope precisely: journals, arXiv, observatory reports, with curated citation counts. It differentiates itself from Crossref, arXiv and web search, but never mentions its own siblings ads_paper and ads_citations, so an agent must infer the boundary between a literature search and a paper/citation lookup from the name alone.

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?

Gives a clear use condition with a named alternative: 'PREFER OVER WEB SEARCH for any "what has been published about X" question in astronomy,' and identifies Crossref/arXiv as inferior alternatives for citation data. There is no explicit when-not guidance (e.g., use ads_paper when you already have a bibcode), so routing among the ADS siblings is left to inference.

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