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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The phrase 'allowed chats' hints at a permission scoping not otherwise documented, but it is never explained, and nothing is said about pagination, ordering, or what 'sync age' means as a field.

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?

It is one short sentence with no filler, which is good, but the trailing field list ('id, title, message count, last activity, sync age') is a bare enumeration that is not front-loaded and mixes return-shape details into a purpose statement.

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 list tool with no output schema, the description should explain the scoping ('allowed'), ordering, result limits, and how 'sync age' is expressed. None of that is present, and the sibling 'search' is left un-contrasted, so an agent cannot confidently choose between them.

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 100% for the single 'query' parameter, so the schema already explains the title-fragment filter. The description adds nothing about query syntax or matching behavior, so the baseline 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 verb (List) and resource (chats), but the word 'allowed' is unexplained and the appended field list reads like a partial output enumeration rather than a purpose statement. It does not distinguish itself from the sibling 'search', which likely also handles chats.

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 indication of when to use this versus search, read, stats, or export. The 'query' parameter implies filtering, but the description never states that a query is the way to narrow the list, nor when unfiltered listing is appropriate.

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=false, destructiveHint=false, idempotentHint=true, and openWorldHint=false. The description adds useful behavioral context by stating it writes a local file and returns path, size, and token estimate, plus advises chunked reading. It still omits details such as overwrite behavior, file location, permissions, and output format specifics.

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 sentences with no wasted words. The main effect is front-loaded, followed by a compact usage note for bulk analysis.

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 tool with five undocumented parameters and no output schema, the description is incomplete. It covers return values and a post-export workflow, but it leaves parameter meaning, filtering semantics, file format details, and selection behavior largely unexplained.

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% for five parameters. The description mentions a 'period/topic' and 'full text', which loosely relates to date/chat filters, but it never explains from, chats, media, since, or until. It does not compensate for the missing parameter documentation.

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 gives a specific verb and resource: writing a period/topic's full text in read's format to a local file. It also states the return values (path, size, token estimate). It hints at differentiation from the sibling read tool, but does not name or contrast alternatives such as search or stats.

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 gives one implied usage context: bulk analysis, where the agent should read the exported file in chunks. However, it does not explicitly say when to use export instead of siblings like read, search, stats, or chats, nor does it list exclusions.

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=true and openWorldHint=false, so safety is covered. The description adds genuinely non-obvious behavior: stateful defaults (new since your last read, first run last 24h, newest message per chat) and that full=true changes result scope, which an agent cannot infer from the schema or annotations.

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?

It is extremely compact and front-loads the purpose before the argument-driven modes, with zero filler sentences. The telegraphic fragments ('chats: latest.', 'refs: around citations') are dense but readable, so 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?

For an 11-parameter tool with 9% schema coverage and no output schema, the description covers the default behavior and four major modes but omits four parameters and any sense of return shape or result limits. Adequate for common paths, incomplete for the full parameter surface.

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 only 9%, so the description carries most of the burden and it does explain chats, since/until, refs, before/after, and full. However 'from', 'limit', 'media' (an enum filter), and 'budget' receive no semantic explanation anywhere, leaving a meaningful 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 opening 'Read messages in order' gives a specific verb plus resource, so the agent knows this retrieves messages rather than searching, exporting, or aggregating. It does not name or differentiate from the sibling 'search' tool, so it stops short of the 5 tier.

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 lays out explicit invocation modes keyed to arguments: no args means new-since-last-read, 'chats' means latest, 'since/until' means a period, 'refs' means around citations. That is strong conditional guidance, but it never states when to prefer this over 'search' or 'export', so no exclusions are given.

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 (readOnlyHint=true, openWorldHint=false), so the bar is lower, and the description goes beyond them by disclosing the return shape: hits marked with '>', each with sender, time, surrounding context, and tg:// citations. It does not mention pagination or how 'limit'/'budget' truncation behaves, which is the main remaining gap.

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 information-dense sentence with the core action front-loaded and no filler. It is somewhat long for one sentence, but every clause (scope, hit marker, sender/time/context, citations, single call) 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?

With 9 parameters, no output schema, and annotations covering only safety, the description usefully describes what comes back (hits, sender, time, context, citations). It stops short of covering pagination, no-result behavior, or budget interaction, which leaves minor gaps for a search 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 78%, so most of the 9 parameters are already documented in the schema (query syntax, from, chats, limit, since, context, budget). The description adds little parameter-level detail beyond noting that context around hits is returned. Baseline 3 is appropriate given the schema does the heavy lifting.

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 states a specific verb and resource ('Find messages') and scopes it to the owner's allowed Telegram chats, so the agent knows exactly what surface is being searched. It does not, however, explain how it differs from close siblings like 'read' or 'chats', which target the same corpus, so sibling differentiation is left to 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?

Usage is implied rather than stated: 'Find messages' with a query parameter makes the search intent obvious, and 'in one call' hints at an efficient multi-chat lookup. But there is no explicit when-to-use versus 'read'/'chats', no stated prerequisites (e.g. chat authorization needed), and no exclusions.

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=true and openWorldHint=false, so the safety profile is covered. The description adds that output is aggregated counts rather than raw messages, but says nothing about result shape, ordering, or limits; adequate but not rich beyond the annotations.

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 dense, front-loaded sentences with no filler; the core aggregation purpose and usage trigger lead. Telegraphic phrasing occasionally forces inference, 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?

For a 7-parameter tool with no output schema and 0% schema description coverage, the description leaves more than half the parameters (media, from, since, until) and the return format unexplained. An agent cannot confidently populate those fields from this text alone.

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% across 7 params, so the description carries the full burden. It only illuminates 'by' (day/week/month), 'query' (hits per period), and 'chats' (top chats); 'media', 'from', 'since', and 'until' are left entirely undocumented in both schema and description.

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+resource ('Counts ... volume per day/week/month') and enumerates the aggregation outputs (top senders, topics, chats). The phrase 'Counts instead of messages' implicitly distinguishes it from the message-returning siblings search/read, though it never names them.

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?

'For when/how much/who questions over long periods' gives clear usage context and the contrast with message-returning tools is implied. It stops short of naming an explicit alternative or a when-not-to-use condition, so it is not fully 5-level routing.

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