Agam

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the 'Read-only' phrase is largely redundant. The description does add genuine scope disclosure beyond the annotations: private evidence is inaccessible and only stable IDs (not arbitrary paths/URLs) are accepted, which is meaningful boundary information for an agent.

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?

Two tight sentences with the core action front-loaded and constraints trailing. The enumeration of return values (INR/paise, precision, source, freshness) is somewhat expendable given a dedicated output schema exists, but it does not bloat the definition.

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?

A single-parameter read tool with full schema coverage, an output schema, and annotations covering safety; the description's additional access-scope limits complete the picture. Nothing essential to correct invocation is missing, though naming the sibling search tool would have closed the last gap.

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% and the single 'id' parameter already documents that it is a stable published content ID and never a path or URL. The description reinforces this with 'stable ID returned by search' but adds no new format, pattern, or lookup semantics, so the baseline of 3 applies.

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 (retrieve) and resource (a stable content ID), and the title clarifies the resource as a public journal record. It implicitly points at the sibling by saying the ID is 'returned by search', though it never names search_content directly, so sibling differentiation requires a small inference.

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 phrase 'a stable ID returned by search' establishes the correct usage sequence (search first, then fetch by ID), and the closing clause gives explicit exclusions: private evidence and arbitrary paths are unavailable. No alternative tool is named outright, but the when-to-use context is clear.

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

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

Annotations already declare read-only, idempotent, closed-world, non-destructive, so the bar is lower. The description still adds real behavior: a one-hour cursor expiry, a 100-record ceiling, and an explicit statement that private/generated/external content is excluded from results.

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?

Three short sentences, each earning its place: purpose, usage sequencing, then constraints. The most decision-relevant scoping statement comes first.

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 an output schema present, return values need not be explained, and the description covers scope, pagination and cursor lifetime. The one material gap is that the four `kind` values are never explained, so an agent cannot know which to pass.

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 75% and the q, limit and cursor descriptions already carry 'literal words', default/max page size, and cursor expiry. The description largely repeats those facts and adds no explanation of the `kind` enum (page/summary/cost/work), which is undocumented in both places.

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?

Specific verb+resource: 'Search literal words in public normalized journal records.' The scope word 'public normalized' distinguishes it from a generic search, and the line 'Use before reading a returned ID' implies the sibling get_content, though it never names it.

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?

Provides sequencing guidance ('Use before reading a returned ID') and rules out categories ('No private results, generated answers or external fetches'). It stops short of explicitly naming get_content as the alternative, so the routing is inferred rather than stated.

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