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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint=false), and the description adds genuinely new context: it depends on an optional `classify` extra and degrades to an install hint if absent. That dependency/failure-mode disclosure is exactly the kind of behavior annotations can't express.

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 lines with zero filler; the purpose leads, followed by invocation mechanics and the dependency caveat. Every sentence earns its place.

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?

An output schema exists, so return values need no explanation. The description covers purpose, input format, the schema-discovery trick, and the optional-dependency caveat — enough to call the tool correctly, with only the SystemProfile field structure left to a follow-up empty-string call.

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 0% and the single parameter has no description, so the description must compensate. It does explain the input is a JSON-encoded SystemProfile and that an empty string returns the schema, but it never says what fields the profile requires — the agent must make a discovery call to learn the shape.

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 — 'Classify an AI system's EU AI Act risk tier' — plus a differentiator ('with pinpoint citations'). The sibling tools are all MiCAR-register related, so the EU AI Act framing alone cleanly separates this tool from every alternative.

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 explains how to invoke it ('Pass a SystemProfile as JSON; pass an empty string to get the schema') but never states when to use it versus the MiCAR siblings or what prerequisites must hold before calling. Usage is operational rather than selective, leaving selection to inference.

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 readOnlyHint, idempotentHint and a closed world, so the safety profile is covered. The description adds genuinely new behavior: the result is 'cited candidate findings pending human review' and the tool requires the optional `lint` extra, degrading to an install hint when absent — a real prerequisite/edge-case disclosure.

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 tight sentences, front-loaded with the action, then output semantics, then the dependency caveat. No filler or repetition of the name.

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?

An output schema exists, so return values need not be described. The description still covers the key operational facts an agent needs before calling: what it checks, that findings are candidates needing human review, and the optional-extra prerequisite with fallback behavior.

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?

Only one parameter with 0% schema description coverage, so the schema says nothing about `whitepaper_json`. The description partly compensates by marking the input as JSON ('draft MiCAR white paper (JSON)'), but it gives no shape, encoding, or required-fields guidance.

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 (lint) plus a specific resource (draft MiCAR white paper as JSON) and the rule set it checks against (Annex I-III). None of the siblings (register search/summary/changes, AI Act classification) overlap with linting, so the agent can route to it unambiguously.

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?

Usage is implied by the resource: use it when you have a draft white paper to check. There is no explicit when-not guidance and no named alternative (e.g., why not just read the Annex rules manually), so it stops at implied context.

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 readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description adds one useful behavioral fact — that each record indicates whether the entry is still listed in the latest snapshot — but omits how far back 'recent' extends and any pagination/freshness behavior, so it adds only moderate value.

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 fragments with the core purpose front-loaded and no padding. The change_type line is slightly manual-like but still earns its place as a filter summary.

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?

An output schema exists, so return values need not be spelled out, and the record-listing semantics are noted. However, with zero schema description coverage, the description should still clarify the limit/recency semantics; that omission leaves the definition only minimally complete for a delta-listing tool.

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 0% and both parameters are undocumented in the schema. The description restates the change_type enum values already present in the schema but never explains the 'limit' parameter or the meaning of 'recent', so it does not compensate for the coverage gap.

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 names a specific resource ('Recent register movement: new filings, changed entries, removals'), so an agent immediately knows this is a change/delta feed. It does not, however, contrast itself with close siblings like search_micar_register or micar_register_summary, leaving the agent to infer the distinction.

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?

No guidance on when to choose this delta tool over search_micar_register or micar_register_summary, and no prerequisites or exclusions are stated. The enumeration of change_type values is parameter detail, not usage guidance.

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 readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered. The description adds almost nothing beyond that — it does not say whether data is live or cached, how registers are grouped, or what 'coverage' is measured against.

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?

A single sentence with no filler and the core payload front-loaded. The phrasing is slightly telegraphic ('format coverage'), but it wastes no space.

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 parameters, an output schema covering the return values, and full annotation coverage, the description is nearly sufficient. The remaining gap is routing: an agent gets no signal about when to pick this over micar_register_changes or search_micar_register.

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?

There are zero input parameters and schema coverage is 100%, so the baseline is 4. Nothing further about parameters is needed or expected.

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 names the specific resource (MiCAR register, white paper formats) and the exact output shape (current totals and format coverage), which clearly separates it from search_micar_register and micar_register_changes. It lacks an explicit verb ('returns'/'lists'), but the meaning is unambiguous.

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?

No when-to-use or when-not-to-use guidance is given, and no sibling is named. An agent must infer from the word 'summary' that this is the aggregate-overview tool rather than the search or change-history tools.

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 cover the safety profile (readOnly, idempotent, openWorld), so the bar is lower. The description goes beyond them with genuinely useful operational context: results come 25 at a time with a truncated flag, and responses carry entry_id, source file, snapshot date, data_age_days and a stale flag.

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 the core purpose in the first line, then one line per parameter with no filler. Slightly clunky line-wrapping that splits a sentence across lines, but nothing is wasted.

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?

Complete for a filtered search: an agent knows the key, the filters, the paging model and the freshness signals. Return-value detail beyond the output schema is a bonus rather than a 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?

With 0% schema description coverage the description must carry the full load, and it does: query is documented as case- and accent-insensitive substring or exact LEI, register_slug's enum values are listed with meaning, member_state is given as a two-letter code with examples, and offset is tied to the 25-per-page/truncated paging model.

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 with scope: 'Search the ESMA interim MiCAR register by entity name or LEI.' The name/LEI lookup key clearly separates it from sibling tools like micar_register_summary and micar_register_changes, though it never names those alternatives explicitly.

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?

Usage is implied by the query semantics (entity-name substring or exact LEI), but there is no statement of when to reach for this tool over micar_register_summary or micar_register_changes, and no exclusions or prerequisites.

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