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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and a closed-world scope, so the safety profile is fully covered. The description does add one genuine behavioral fact beyond the annotations: results are returned ranked best-match-first. That is useful, but nothing is said about result count, pagination, or what a match against a book versus a passage looks like.

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 opening sentence is tight and front-loaded, which is good. The second sentence is a dense semicolon-joined list that mixes corpora, features, and reading modes without a clear subject, so it costs attention without fully resolving what the tool searches.

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 single-parameter search with rich read-only annotations and no output schema, the definition is minimally adequate: the agent knows what to pass and that it is safe. It still leaves the agent guessing about result volume and how the ranked results relate to the follow-up get_reading/get_shabad tools.

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% with a single required 'q' parameter, and the schema already gives examples ('Japji or humility'), so the baseline of 3 applies. The description adds no query syntax guidance (phrase vs. keyword, bani names, Ang references) beyond what the schema provides.

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 curated readings') and adds a ranking promise ('best match first'), which is more than a restatement of the name. The trailing clause about Gurbani, plans, Ang and shabad lookup describes corpus coverage rather than differentiating it from siblings like get_shabad or get_reading, so sibling separation is only partial.

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?

There is no statement of when to pick this over get_reading, get_shabad, or list_readings, nor any exclusions or prerequisites. The mention of 'Gurbani: daily shabad, plans, search, Ang and shabad lookup' reads as a domain listing rather than routing guidance, leaving the agent to infer when searching beats a direct lookup.

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